© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22806
    Prev
    Next
    INDEX
    Explanations

    tenant

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    翃
    -2.56
     {
    -2.50
    🫃
    -2.44
    她
    -2.33
    iding
    -2.30
    ktionen
    -2.30
    놋
    -2.17
    yskland
    -2.17
    倌
    -2.14
    ignements
    -2.13
    POSITIVE LOGITS
    -
    2.81
     schein
    2.52
    in
    2.23
    Both
    2.17
    there
    2.17
    すでに
    2.11
    ing
    2.09
    鏵
    2.09
    which
    2.06
    ON
    2.05
    Activations Density 0.001%

    No Known Activations