© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67263
    Prev
    Next
    INDEX
    Explanations

    XML, code, and scientific text

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

    URLs in HTML and programming code.

    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_10/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
     
    -2.66
    ↵
    -2.45
     &
    -2.28
     *
    -2.25
     i
    -2.16
    o
    -2.13
     these
    -2.09
     involucra
    -2.05
     ect
    -2.03
     [
    -1.99
    POSITIVE LOGITS
    熺
    2.70
    𖣘
    2.69
    塒
    2.59
    筇
    2.56
    鯓
    2.55
     MEXICO
    2.53
    which
    2.53
    萣
    2.50
    鰨
    2.39
     vedi
    2.34
    Activations Density 0.000%

    No Known Activations