© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117083
    Prev
    Next
    INDEX
    Explanations

    subject/described

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

    The neuron activates on Ruby RSpec DSL keywords and block delimiters (e.g. describe, context, it, before, let, do, end).

    oai_token-act-pair · o4-miniTriggered 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
    Mush
    -0.71
    skill
    -0.69
     сер
    -0.69
     ơi
    -0.68
     Mg
    -0.68
    governor
    -0.66
     Pre
    -0.65
     دسته
    -0.65
     між
    -0.65
     타
    -0.65
    POSITIVE LOGITS
     subject
    1.51
    subject
    1.47
     described
    1.46
    described
    1.34
    Subject
    1.08
     subjected
    1.01
    pending
    0.96
     subjects
    0.92
    fehlungen
    0.91
     subjecting
    0.87
    Activations Density 0.026%

    No Known Activations