© 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. 14504
    Prev
    Next
    INDEX
    Explanations

    FIG, Part, Experiment, season, section numbers

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

    The neuron specializes in spotting numeric tokens—especially multi-digit and decimal numbers (e.g. “46.75,” “106.5,” “32.75,” etc.).

    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
     from
    -3.03
     with
    -2.92
     by
    -2.36
     without
    -2.19
     on
    -2.17
     while
    -2.14
     before
    -2.09
     for
    -1.99
     in
    -1.90
     through
    -1.82
    POSITIVE LOGITS
     jezt
    1.84
     konkret
    1.77
    
    1.70
    喾
    1.65
     professione
    1.63
     katalog
    1.62
     Dinas
    1.61
    鶫
    1.60
     eſſ
    1.60
     ſou
    1.60
    Activations Density 0.054%

    No Known Activations