© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67060
    Prev
    Next
    INDEX
    Explanations

    variable definitions and assignments

    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
    Not in Any Lists

    No Comments

    Negative Logits
     roś
    -1.31
     ซี
    -1.27
     divent
    -1.20
     reflejo
    -1.19
    のではない
    -1.19
    électricité
    -1.18
     insanely
    -1.17
     dezelve
    -1.17
    tiliz
    -1.16
     meub
    -1.14
    POSITIVE LOGITS
     all
    1.63
     in
    1.42
     how
    1.30
     because
    1.27
     only
    1.25
     still
    1.25
     with
    1.21
     (
    1.20
     just
    1.18
     mainly
    1.17
    Activations Density 0.071%

    No Known Activations