© 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. 3331
    Prev
    Next
    INDEX
    Explanations

    summing calculating tally

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

    The neuron fires on tokens inside code documentation comments (e.g. JSDoc comment blocks).

    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
     vectors
    -0.77
     magyar
    -0.77
     své
    -0.77
    śród
    -0.75
    glTranslatef
    -0.72
     pertenece
    -0.71
    httpClient
    -0.71
    但她
    -0.71
    hfill
    -0.70
    JsonNode
    -0.70
    POSITIVE LOGITS
    Tally
    0.94
     summing
    0.93
     Tally
    0.93
    加
    0.86
    앓
    0.84
     calculating
    0.84
    累
    0.84
    Tot
    0.84
     tally
    0.81
    Calculating
    0.81
    Activations Density 0.000%

    No Known Activations