© 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. 130845
    Prev
    Next
    INDEX
    Explanations

    links to documentation or resources

    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
     мужская
    -1.37
    忽视
    -1.36
     toutefois
    -1.34
     néanmoins
    -1.31
     большин
    -1.30
     geliefert
    -1.23
     certamente
    -1.14
     fiable
    -1.14
    albeit
    -1.14
     MICHAEL
    -1.12
    POSITIVE LOGITS
     AWESOME
    1.20
    ܡ
    1.18
     pertumbuhan
    1.15
    unnitel
    1.14
     begin
    1.13
     takes
    1.13
    windig
    1.11
     phenomenal
    1.10
    ViewChild
    1.10
     bordada
    1.09
    Activations Density 0.020%

    No Known Activations