© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106431
    Prev
    Next
    INDEX
    Explanations

    stand the test of time

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

    The neuron strongly responds to file‐extension tokens (especially “.h” header extensions, and similarly “.txt”).

    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
    pheres
    -0.70
    öfe
    -0.69
     sphere
    -0.68
     نوم
    -0.66
    $:
    -0.65
    Bombay
    -0.64
    menade
    -0.63
    Jó
    -0.63
     spheres
    -0.62
    Lod
    -0.62
    POSITIVE LOGITS
    DebuggerStep
    0.76
    Ori
    0.70
     RIV
    0.67
     кү
    0.67
     communications
    0.65
     Pape
    0.64
     تلویزیون
    0.64
    Internal
    0.64
     Batalla
    0.63
    internal
    0.63
    Activations Density 0.042%

    No Known Activations