© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33073
    Prev
    Next
    INDEX
    Explanations

    COURT OF APPEALS

    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
     for
    -2.38
     with
    -2.31
     ostensibly
    -2.30
     blatantly
    -2.28
     without
    -2.27
     first
    -2.23
     when
    -2.20
     vehemently
    -2.17
     after
    -2.16
     radically
    -2.16
    POSITIVE LOGITS
     splendid
    2.17
     overarching
    2.17
     soooo
    2.17
     Dinas
    2.16
     AMAZING
    2.13
     !!!!
    2.13
     dismal
    2.11
     masterful
    2.08
     alluring
    2.08
     tumultuous
    2.06
    Activations Density 0.023%

    No Known Activations