© 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. 2727
    Prev
    Next
    INDEX
    Explanations

    do not edit generated files

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

    This neuron detects boilerplate “do not edit/modify this file” warnings in autogenerated source‐code or document headers.

    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
     niebies
    -0.88
    AVY
    -0.68
    時点で
    -0.67
     ī
    -0.66
     jakby
    -0.65
     kepala
    -0.65
    forza
    -0.65
     distillation
    -0.64
     diphtheria
    -0.64
    हम
    -0.63
    POSITIVE LOGITS
    ѓ
    0.78
    Studios
    0.77
    jul
    0.77
    ichtliche
    0.76
    время
    0.75
    -_-
    0.74
    ្រ
    0.73
    eneral
    0.72
    nitus
    0.71
    ↢
    0.71
    Activations Density 0.027%

    No Known Activations