© 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. 64562
    Prev
    Next
    INDEX
    Explanations

    scientific classification codes

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

    numerical classification codes in scientific or technical documents.

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

    The neuron fires on numeric tokens or digit sequences (e.g. classification codes, years, identifiers).

    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
     that
    -1.06
    U
    -0.94
     will
    -0.93
    附近的
    -0.93
    auces
    -0.91
     going
    -0.90
    stringBuffer
    -0.90
     соціаль
    -0.89
     caratteri
    -0.89
    부터
    -0.88
    POSITIVE LOGITS
     autres
    1.28
    istán
    1.27
    sistors
    1.26
    xically
    1.23
    艄
    1.22
    liquez
    1.16
     devem
    1.14
    ulação
    1.12
    stuhl
    1.10
     кровать
    1.09
    Activations Density 0.014%

    No Known Activations