© 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. 34-GEMMASCOPE-RES-131K
    4. 11998
    Prev
    Next
    INDEX
    Explanations

    surgeons and television characters

    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_34/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
    UT
    -0.76
     biomarker
    -0.73
    며
    -0.73
    ([{
    -0.70
     دهید
    -0.70
    obio
    -0.68
    鄭
    -0.68
     Fonds
    -0.67
     коро
    -0.66
    ştir
    -0.66
    POSITIVE LOGITS
     Hawkeye
    0.90
     surgeons
    0.84
    gadier
    0.79
     Allo
    0.79
    проце
    0.76
     feathered
    0.76
    Allo
    0.76
     priceless
    0.76
     Snell
    0.75
     Radar
    0.75
    Activations Density 0.016%

    No Known Activations