© 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. 38615
    Prev
    Next
    INDEX
    Explanations

    Drug possession

    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
     in
    -2.02
     on
    -1.98
     with
    -1.93
     at
    -1.81
     or
    -1.68
     by
    -1.48
     for
    -1.47
     from
    -1.43
     as
    -1.41
     without
    -1.41
    POSITIVE LOGITS
     isolamento
    1.58
    츨
    1.49
    などを
    1.44
     gän
    1.42
    ztes
    1.41
     nombreuses
    1.38
     nunmehr
    1.37
     (~(
    1.35
     Boletín
    1.35
     Reised
    1.30
    Activations Density 0.003%

    No Known Activations