© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59201
    Prev
    Next
    INDEX
    Explanations

    is preserved

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

    The neuron is responding to high-level document structure markers—section titles, metadata field names, and other heading/label tokens.

    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
     kwamba
    -0.87
     dialogo
    -0.82
     situations
    -0.80
     Celle
    -0.80
     チェーン
    -0.77
     actually
    -0.77
     qashqai
    -0.75
     Entered
    -0.75
     others
    -0.75
     Portanto
    -0.74
    POSITIVE LOGITS
     Mérimée
    0.74
     отношению
    0.74
    Trung
    0.74
     }\
    0.73
    enada
    0.72
    Và
    0.72
    CIA
    0.71
    Another
    0.71
    iltà
    0.71
     mauvaises
    0.71
    Activations Density 0.002%

    No Known Activations