© 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. 16565
    Prev
    Next
    INDEX
    Explanations

    /* followed by '=', Green followed by tip, You followed by are

    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
     desmotiv
    -1.22
     their
    -1.16
     his
    -1.07
     him
    -1.04
     my
    -0.96
    而已
    -0.96
    mohon
    -0.93
     honestly
    -0.93
    🪘
    -0.92
    ==$
    -0.92
    POSITIVE LOGITS
    artigen
    1.00
    了下去
    1.00
    According
    0.99
    kaj
    0.93
    ք
    0.92
    Ciclo
    0.91
     الصيف
    0.90
    schuhe
    0.90
     çeşitli
    0.90
    최
    0.89
    Activations Density 0.000%

    No Known Activations