© 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. 30948
    Prev
    Next
    INDEX
    Explanations

    news, Valentine, Q, Interesting

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

    The neuron activates on multi‐digit numeric tokens (e.g. version numbers, years, or other numeric constants).

    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
     setzt
    -0.73
     يف
    -0.70
    立刻
    -0.70
     rice
    -0.69
     jao
    -0.69
     Farms
    -0.68
     окна
    -0.68
    租赁
    -0.68
    oude
    -0.68
     setzen
    -0.68
    POSITIVE LOGITS
    ộm
    0.92
    ケート
    0.79
    Affirmed
    0.79
    সূত্র
    0.75
    ución
    0.71
    行政
    0.71
    LLOW
    0.70
     Cataloging
    0.69
    ění
    0.68
    Firewall
    0.68
    Activations Density 0.002%

    No Known Activations