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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54495
    Prev
    Next
    INDEX
    Explanations

    Walter Scott

    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
     (
    -1.29
     in
    -1.13
     where
    -1.05
     ((
    -0.91
     «
    -0.90
    もあって
    -0.88
     (!
    -0.88
     bez
    -0.88
     engraçadas
    -0.85
     remembered
    -0.85
    POSITIVE LOGITS
     hervorge
    1.14
     dezelfde
    1.10
    Vino
    1.08
     hetzelfde
    1.08
     mungkin
    1.07
     voordelen
    1.06
     geboten
    1.05
     angezeigt
    1.05
    zieher
    1.05
     berechtigt
    1.04
    Activations Density 0.007%

    No Known Activations