© 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. 98283
    Prev
    Next
    INDEX
    Explanations

    various specific terms and labels

    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
     Gó
    -1.23
     Trá
    -1.11
    .*")]
    -1.08
    leeve
    -1.07
    tionnaire
    -1.06
    "){
    
    -1.05
    neous
    -1.04
    Aiheesta
    -1.03
    >.</
    -1.02
    határoz
    -1.01
    POSITIVE LOGITS
     in
    1.34
    すべて
    1.01
    ÍNDICE
    0.98
     настолько
    0.98
    OBJETIVOS
    0.92
    人了
    0.91
    全ての
    0.90
    秃
    0.88
     is
    0.87
     behöver
    0.86
    Activations Density 0.254%

    No Known Activations