© 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. 106253
    Prev
    Next
    INDEX
    Explanations

    exception details

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

    The neuron is picking up on the dot “.” punctuation used in code (e.g. member‐access and namespace separators).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     違い
    -0.73
    Tahoma
    -0.73
    рій
    -0.72
     lặng
    -0.69
    givenchy
    -0.69
    Otros
    -0.69
     intents
    -0.69
     defer
    -0.68
    Teresa
    -0.67
    jątk
    -0.67
    POSITIVE LOGITS
    Inner
    1.32
     inner
    1.30
     Inner
    1.19
    inner
    1.18
     INNER
    1.12
     innermost
    0.95
     Source
    0.94
     source
    0.93
    Source
    0.92
    INNER
    0.88
    Activations Density 0.023%

    No Known Activations