© 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. 64518
    Prev
    Next
    INDEX
    Explanations

    smoke detection and alarm

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    .”
    -3.36
    7
    -2.95
    ri
    -2.95
    as
    -2.86
    re
    -2.84
    ’
    -2.83
    ner
    -2.67
    5
    -2.64
    2
    -2.63
    The
    -2.61
    POSITIVE LOGITS
    鬭
    3.77
    dalam
    2.67
    Ꮸ
    2.63
    ᜀ
    2.61
    肜
    2.56
    耵
    2.55
    𞤥
    2.53
    𞤢
    2.47
    zdroj
    2.39
    辄
    2.39
    Activations Density 0.011%

    No Known Activations