© 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. 22-GEMMASCOPE-RES-131K
    7. 64332
    Prev
    Next
    INDEX
    Explanations

    configuration keys and identifiers

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    setIcon
    -0.96
    blis
    -0.93
     and
    -0.93
    hate
    -0.91
    pagnole
    -0.86
    carrot
    -0.85
    ामी
    -0.84
    lovak
    -0.84
    sca
    -0.83
     Asimismo
    -0.83
    POSITIVE LOGITS
    ilité
    1.23
    setObjectName
    1.02
    litian
    1.00
    }_
    0.96
     name
    0.96
     petitioner
    0.95
     ""],
    0.95
    ȷ
    0.94
    rió
    0.94
    ₖ
    0.92
    Activations Density 0.035%

    No Known Activations