© 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. 10-GEMMASCOPE-RES-131K
    7. 6858
    Prev
    Next
    INDEX
    Explanations

    packing and packed items

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    .
    -2.28
    ↵↵
    -2.28
    '.'
    -2.22
    '~
    -1.95
    *
    -1.89
    '!
    -1.89
    </h3>
    -1.88
    '|
    -1.87
    ⪧
    -1.83
     完了
    -1.77
    POSITIVE LOGITS
    pack
    2.06
    </b>
    2.05
    ஂ
    1.95
    珝
    1.88
    pulseira
    1.82
    5
    1.81
    waar
    1.80
    んでも
    1.80
    atieve
    1.80
     essere
    1.73
    Activations Density 0.014%

    No Known Activations