© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81329
    Prev
    Next
    INDEX
    Explanations

    Apache License, Version 2.0

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

    The neuron fires on numeric tokens—e.g. digits, version numbers, build or directory indices—wherever number strings appear.

    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
    hud
    -0.72
     li
    -0.72
    ────
    -0.71
     check
    -0.69
     Po
    -0.67
    zcan
    -0.67
    早い
    -0.66
    bete
    -0.66
     checking
    -0.66
    scrollY
    -0.66
    POSITIVE LOGITS
    army
    0.79
     GARDEN
    0.77
    jsh
    0.69
    notre
    0.68
     auge
    0.67
    わりに
    0.67
     .;
    0.67
     ISLAM
    0.66
    ellite
    0.66
     Auge
    0.66
    Activations Density 0.077%

    No Known Activations