© 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. 78236
    Prev
    Next
    INDEX
    Explanations

    http:// or code delimiters

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

    The neuron fires on tokens that are purely numeric (i.e. digit sequences representing 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_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
    flutter
    -0.80
    ыз
    -0.77
    линг
    -0.75
     fact
    -0.75
    сыз
    -0.74
     janeiro
    -0.74
    acak
    -0.73
    сми
    -0.72
    ILI
    -0.72
    RTCF
    -0.72
    POSITIVE LOGITS
    ..,
    0.77
    évalu
    0.77
     olhar
    0.75
     чрезвы
    0.73
     rẻ
    0.73
     Wahrnehmung
    0.73
     Anerkennung
    0.71
    の中には
    0.70
    inscription
    0.70
     apresenta
    0.70
    Activations Density 0.006%

    No Known Activations