© 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. 16629
    Prev
    Next
    INDEX
    Explanations

    entities and their properties

    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
    ஐ
    -1.25
    quations
    -1.09
    amna
    -1.05
     Âu
    -1.02
    naa
    -1.00
    pasti
    -0.99
    angsaan
    -0.97
     разнообраз
    -0.96
    entrepreneur
    -0.96
     cantora
    -0.95
    POSITIVE LOGITS
     with
    1.13
    Ensuite
    1.02
     =
    1.00
     two
    0.99
    Now
    0.94
    готовки
    0.94
    zig
    0.93
     подойдет
    0.92
     =(
    0.92
     среда
    0.90
    Activations Density 0.093%

    No Known Activations