© 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. 32593
    Prev
    Next
    INDEX
    Explanations

    programming language operations

    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
    0
    -1.73
    1
    -1.60
    もありました
    -1.48
    ,
    -1.48
    2
    -1.46
    <h3>
    -1.45
    </h3>
    -1.43
    .,
    -1.43
    ldots
    -1.38
    そして
    -1.34
    POSITIVE LOGITS
    濶
    1.72
    大体
    1.66
    IRING
    1.58
    欵
    1.55
    峒
    1.51
     crianças
    1.48
    ñado
    1.48
    ＊＊＊＊
    1.47
    &
    1.47
     vestido
    1.46
    Activations Density 0.001%

    No Known Activations