© 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. 64542
    Prev
    Next
    INDEX
    Explanations

    medical period

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

    punctuation patterns with hyphens or other special characters.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron mainly fires on tokens that are numeric—i.e. digits, years, reference numbers, or other number sequences.

    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
     ។
    -1.09
     stret
    -1.04
    ។
    -1.02
    wać
    -0.99
    スズキ
    -0.98
    閨
    -0.98
     оно
    -0.96
     it
    -0.96
     Olimp
    -0.96
    πουργ
    -0.96
    POSITIVE LOGITS
     Straße
    1.06
    eneral
    1.05
     kateg
    1.04
    像
    0.98
     ideen
    0.98
    efter
    0.97
     lej
    0.96
     francia
    0.95
    ṭ
    0.94
     Periode
    0.94
    Activations Density 0.002%

    No Known Activations