© 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. 32744
    Prev
    Next
    INDEX
    Explanations

    specific industry terms

    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
     also
    -1.90
     similar
    -1.52
     but
    -1.40
     such
    -1.37
     to
    -1.37
     Also
    -1.27
     etc
    -1.27
     with
    -1.26
     includes
    -1.23
     by
    -1.21
    POSITIVE LOGITS
     که
    1.65
     που
    1.65
    juries
    1.39
    Ṅ
    1.34
     الذي
    1.29
     Voiture
    1.29
    ¡¡¡
    1.27
    鳚
    1.25
     teater
    1.25
     formen
    1.25
    Activations Density 0.066%

    No Known Activations