© 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. 32758
    Prev
    Next
    INDEX
    Explanations

    code and explanations

    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
     sig
    -0.82
    [@"
    -0.81
    |>
    -0.79
     eleg
    -0.79
    publique
    -0.77
    ส์
    -0.75
    CTYPE
    -0.75
    ēju
    -0.75
     aventures
    -0.75
    ListItemIcon
    -0.75
    POSITIVE LOGITS
     expectation
    0.99
     haría
    0.96
     skola
    0.93
     expectations
    0.92
     correct
    0.91
    rigue
    0.88
     both
    0.88
    ウル
    0.88
    البته
    0.87
    自分も
    0.86
    Activations Density 0.017%

    No Known Activations