© 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. 107459
    Prev
    Next
    INDEX
    Explanations

    code comments and introductions

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

    The neuron is primarily sensitive to numeric literals (tokens composed of digits) in code or text.

    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
     just
    -1.09
     for
    -0.87
    只是
    -0.86
     first
    -0.83
     all
    -0.81
     from
    -0.77
     whose
    -0.77
     tikai
    -0.77
     most
    -0.76
     (
    -0.75
    POSITIVE LOGITS
    —,
    0.93
    》,
    0.92
     verschillende
    0.88
    tät
    0.88
    **,
    0.85
     ?,
    0.85
     ado
    0.83
    migrationBuilder
    0.83
     ก
    0.83
    uolo
    0.83
    Activations Density 0.000%

    No Known Activations