© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91124
    Prev
    Next
    INDEX
    Explanations

    functionality characterizes genomic elements

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

    document identifiers, reference numbers, and citation elements in legal and technical documents.

    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
     ویتامین
    -0.75
    jutan
    -0.75
     extracted
    -0.73
    admin
    -0.73
    OWER
    -0.71
     Extending
    -0.71
    ﮕ
    -0.70
    ussch
    -0.70
     ATLAS
    -0.69
    prechung
    -0.69
    POSITIVE LOGITS
    thermia
    0.74
     Heil
    0.68
     capacidades
    0.66
     wake
    0.60
    <.
    0.60
    ordum
    0.59
    Heil
    0.59
     conspir
    0.58
    foc
    0.58
    crank
    0.58
    Activations Density 0.053%

    No Known Activations