© 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. 22-GEMMASCOPE-RES-131K
    7. 66844
    Prev
    Next
    INDEX
    Explanations

    terminal, disease, application

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

    technical or scientific terms in documentation and technical questions.

    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_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
     `<
    -1.13
     religieux
    -1.11
    新しく
    -1.09
    ﾕ
    -1.09
    Į
    -1.07
     chimie
    -1.07
    新しい
    -1.07
    .>
    -1.05
    ţiei
    -1.04
     tarda
    -1.04
    POSITIVE LOGITS
     #
    1.13
     COVID
    1.03
     (
    0.98
     in
    0.98
    with
    0.97
     team
    0.95
     What
    0.94
    covid
    0.94
     My
    0.94
     Best
    0.92
    Activations Density 0.072%

    No Known Activations