© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64607
    Prev
    Next
    INDEX
    Explanations

    plist key tags

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

    This neuron fires on numeric literals.

    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
    %)
    -1.12
    </i>
    -1.09
    ícias
    -1.03
    adás
    -1.00
    ции
    -0.99
    也就是
    -0.99
    他
    -0.98
     আপ
    -0.96
    ssymb
    -0.96
    ˜
    -0.95
    POSITIVE LOGITS
    ったのは
    0.93
    Bras
    0.93
     地址
    0.89
     Під
    0.88
    不愧
    0.85
    íč
    0.85
    了许多
    0.84
    athl
    0.84
     volete
    0.82
     fuf
    0.82
    Activations Density 0.012%

    No Known Activations