© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130015
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens (digits, dates, and decimal figures).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    Pet sounds like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    歺
    -1.02
     Thos
    -0.98
    Ты
    -0.97
    later
    -0.96
     CALIF
    -0.93
    Этот
    -0.92
    子どもの
    -0.92
     HUAWEI
    -0.91
    Мон
    -0.91
     Wallflower
    -0.90
    POSITIVE LOGITS
    toprule
    0.98
     funktion
    0.92
     çap
    0.90
     görüntüsü
    0.89
    dailymail
    0.88
     contará
    0.88
    olved
    0.87
    limard
    0.87
    ύ
    0.85
    jooq
    0.84
    Activations Density 0.016%

    No Known Activations