© 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. 54319
    Prev
    Next
    INDEX
    Explanations

    database column definitions

    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
     T
    -1.06
    ház
    -0.99
    ışı
    -0.95
    NSNotification
    -0.94
     V
    -0.94
     small
    -0.93
     long
    -0.91
    either
    -0.90
     all
    -0.90
     (
    -0.90
    POSITIVE LOGITS
     الإنترنت
    1.20
     `/
    1.16
     '');
    1.16
     humanidad
    1.11
     gik
    1.09
     '#'
    1.09
     キッチン
    1.07
     GOtt
    1.06
    Hersteller
    1.06
     jezt
    1.06
    Activations Density 0.002%

    No Known Activations