© 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. 90958
    Prev
    Next
    INDEX
    Explanations

    module dependencies

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

    This neuron activates on integer numeric literals in code (e.g., standalone numbers).

    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
     if
    -1.02
     for
    -0.98
     gdyby
    -0.84
     Many
    -0.82
     թվ
    -0.78
     mainly
    -0.76
    tization
    -0.74
    它
    -0.73
     just
    -0.73
     they
    -0.71
    POSITIVE LOGITS
     bedo
    0.93
    Produkte
    0.90
    ม้
    0.89
    פון
    0.85
    ’;
    0.83
    っぷ
    0.83
    SARAH
    0.82
    CONCLUS
    0.81
    ?;
    0.81
     cana
    0.81
    Activations Density 0.011%

    No Known Activations