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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106514
    Prev
    Next
    INDEX
    Explanations

    Physiological

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

    Chinese or East Asian names and terms, particularly when they appear in biographical or historical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on numeric tokens—digits or multi-digit numbers (e.g., years, quantities, counts).

    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
    🦪
    -0.80
    無論
    -0.78
    сной
    -0.77
    Пока
    -0.77
    жден
    -0.75
     焼
    -0.75
    କ
    -0.74
     Empress
    -0.74
     rät
    -0.73
    ниме
    -0.71
    POSITIVE LOGITS
     Left
    0.93
    rights
    0.88
     left
    0.86
     office
    0.85
    Left
    0.84
    left
    0.81
    dit
    0.77
    terrorism
    0.76
     naz
    0.76
     Office
    0.76
    Activations Density 0.010%

    No Known Activations