© 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. 79117
    Prev
    Next
    INDEX
    Explanations

    Secondary screening

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

    The neuron fires on multi‐digit numeric tokens, especially large numbers and statistics.

    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
     Gauthier
    -0.81
    有力
    -0.77
     TFT
    -0.74
     Waktu
    -0.72
     Colón
    -0.70
     anual
    -0.68
    🆂
    -0.68
     serie
    -0.68
     moyen
    -0.68
     crudo
    -0.68
    POSITIVE LOGITS
     indoor
    0.91
     arena
    0.90
     Arena
    0.84
    arena
    0.82
    Arena
    0.77
    setVerticalGroup
    0.76
     Operator
    0.74
     Aloe
    0.73
    ंत
    0.73
     Rif
    0.72
    Activations Density 0.037%

    No Known Activations