© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31870
    Prev
    Next
    INDEX
    Explanations

    Expression of, Dementia is

    np_acts-logits-general · gemini-2.5-flash-lite

    computer code elements, particularly in programming files like source code or documentation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    шают
    -0.93
     Uti
    -0.81
    velles
    -0.81
     sams
    -0.77
    МЕН
    -0.74
    jestel
    -0.74
    OfSize
    -0.73
     рецеп
    -0.73
     weken
    -0.72
     geïsole
    -0.72
    POSITIVE LOGITS
    віть
    0.93
     этих
    0.91
     Existing
    0.89
    燾
    0.87
    snprintf
    0.85
    merate
    0.85
    Dota
    0.84
     besoin
    0.83
     but
    0.82
     Read
    0.82
    Activations Density 0.000%

    No Known Activations