© 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. 25123
    Prev
    Next
    INDEX
    Explanations

    NOT FOR PUBLICATION

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

    The neuron fires on tokens written entirely in uppercase (e.g. acronyms, headings, or all-caps words).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     by
    -1.76
     in
    -1.73
     before
    -1.63
     only
    -1.57
     from
    -1.53
     during
    -1.49
     both
    -1.47
     just
    -1.45
     to
    -1.45
     these
    -1.44
    POSITIVE LOGITS
     ſu
    1.63
     け
    1.41
    erving
    1.40
     ܗ
    1.37
    %">
    1.37
    enddo
    1.35
    裢
    1.34
     cliquer
    1.34
    //</
    1.33
    vité
    1.33
    Activations Density 0.001%

    No Known Activations