© 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. 10-GEMMASCOPE-RES-131K
    7. 72092
    Prev
    Next
    INDEX
    Explanations

    safety precautions and care

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     then
    -1.86
     by
    -1.84
     not
    -1.55
     also
    -1.45
     about
    -1.26
     only
    -1.26
     now
    -1.23
     eventually
    -1.20
     than
    -1.20
     still
    -1.19
    POSITIVE LOGITS
    Both
    1.39
     ESPEC
    1.23
    cześ
    1.22
    onekana
    1.19
    Those
    1.17
     triomphe
    1.15
    ꉂ
    1.13
    şek
    1.13
     unimagin
    1.13
    likleri
    1.12
    Activations Density 0.033%

    No Known Activations