© 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. 22-GEMMASCOPE-RES-131K
    7. 65101
    Prev
    Next
    INDEX
    Explanations

    durations of time

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

    The neuron fires on numeric tokens (e.g. numerals for years, percentages, monetary amounts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     胶
    -0.86
     plupart
    -0.81
    ()+"
    -0.79
     types
    -0.77
    Sizer
    -0.76
     Kurdistan
    -0.76
    に来て
    -0.76
    Qualität
    -0.75
     台中
    -0.75
     Qualität
    -0.74
    POSITIVE LOGITS
    itettura
    1.06
     haja
    1.00
     mélanger
    0.97
    afc
    0.95
     éché
    0.91
    ナー
    0.89
     литров
    0.89
    cketed
    0.87
     Ау
    0.85
    **
    0.85
    Activations Density 0.069%

    No Known Activations