© 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. 10-GEMMASCOPE-RES-131K
    7. 8083
    Prev
    Next
    INDEX
    Explanations

    prove to be

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

    The neuron chiefly detects numeric tokens (i.e. 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_10/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
     ERSITY
    -2.06
    [
    -1.84
    翌日
    -1.83
    inescence
    -1.75
    ſures
    -1.70
     "../../../
    -1.60
    /</
    -1.59
     without
    -1.57
     Tämä
    -1.55
    ]
    -1.55
    POSITIVE LOGITS
     extremamente
    2.06
     também
    2.05
     They
    1.96
    푉
    1.92
    籥
    1.81
     Они
    1.77
     ouvido
    1.76
     colocado
    1.74
     após
    1.73
    とい
    1.72
    Activations Density 0.007%

    No Known Activations