© 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. 54289
    Prev
    Next
    INDEX
    Explanations

    code comments and documentation

    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
     belangrijk
    -1.08
     siquiera
    -1.07
     aiutare
    -0.99
     marié
    -0.95
     continúas
    -0.95
     kiedy
    -0.92
    edded
    -0.92
    erobic
    -0.91
     pulsera
    -0.91
     reproducción
    -0.90
    POSITIVE LOGITS
    vaila
    1.13
     harmonie
    1.06
    licante
    1.00
     Philos
    1.00
    madeus
    0.97
    `,
    
    0.96
     layui
    0.94
    प्र
    0.94
    Meanwhile
    0.94
     guatemala
    0.93
    Activations Density 0.004%

    No Known Activations