© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68101
    Prev
    Next
    INDEX
    Explanations

    code commands and systems

    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
     with
    -1.06
    ;
    -0.97
    褐
    -0.91
     evolving
    -0.88
    '
    -0.86
     all
    -0.83
     држа
    -0.82
     each
    -0.80
    ’
    -0.80
     still
    -0.79
    POSITIVE LOGITS
     oiseau
    1.13
     performed
    1.11
     undertaken
    1.05
     hört
    1.03
     curioso
    1.02
     executed
    1.02
     procedure
    1.02
    ustre
    1.02
     engraçado
    1.00
     sırasında
    0.98
    Activations Density 0.027%

    No Known Activations