© 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. 33576
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

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

    This neuron fires in proportion to tokens that represent numeric values (e.g. literal numbers or symbols whose raw encoding yields a number), effectively detecting number‐like tokens and outputting an activation roughly equal to their numeric value.

    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
    urants
    -1.05
    othes
    -1.01
     sánh
    -0.98
    without
    -0.96
    cketed
    -0.95
    歟
    -0.94
     cuja
    -0.94
    gemene
    -0.94
     Reſ
    -0.93
    affiche
    -0.92
    POSITIVE LOGITS
     you
    1.05
    研究生
    0.94
     уже
    0.92
     people
    0.89
     levure
    0.87
     has
    0.86
    moduleId
    0.84
     time
    0.84
     Ок
    0.84
    вера
    0.83
    Activations Density 0.018%

    No Known Activations