© 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. 65449
    Prev
    Next
    INDEX
    Explanations

    history dates

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

    This neuron detects numeric tokens, especially digits representing years or dates.

    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
     egenskaper
    -1.11
    阵法
    -1.09
     花朵
    -1.09
     やすい
    -1.09
     nuo
    -1.08
     kroppen
    -1.07
    गत
    -1.02
     mètres
    -0.99
    いかがでしたか
    -0.98
    Helvetica
    -0.97
    POSITIVE LOGITS
     eventually
    1.06
     Eventually
    1.05
     offiziell
    0.95
     Szene
    0.91
    还好
    0.91
     vielleicht
    0.90
    ‌های
    0.90
     comum
    0.89
    focusable
    0.89
     entweder
    0.88
    Activations Density 0.047%

    No Known Activations