© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107026
    Prev
    Next
    INDEX
    Explanations

    mechanical fasteners

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron reliably fires on identifiers and path fragments in module import statements (e.g. the names and paths in “import { … } from '…'”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    code, structured data, and technical/programming content (like import statements, class names, and code syntax).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    structured preamble/header metadata that declares sources, fields, or routing information (such as code import statements and email header lines).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ühner
    -0.75
    几分
    -0.75
    愿望
    -0.70
    vbo
    -0.69
    خبار
    -0.69
     agrarian
    -0.68
    vms
    -0.67
     earthquakes
    -0.67
    MBS
    -0.67
    axter
    -0.66
    POSITIVE LOGITS
    Exchange
    0.90
     Pid
    0.89
    ódź
    0.86
    appointment
    0.84
     recipients
    0.83
    Importance
    0.82
     appointment
    0.79
    γο
    0.79
    folder
    0.79
     Appointment
    0.79
    Activations Density 0.058%

    No Known Activations