© 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. 16596
    Prev
    Next
    INDEX
    Explanations

    visual or conceptual contrast

    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
    瑒
    -3.02
    簠
    -2.69
    <bos>
    -2.47
    Mã
    -2.45
    lokal
    -2.39
     绒
    -2.30
    羕
    -2.23
    癭
    -2.22
     実例
    -2.17
    Ꭸ
    -2.17
    POSITIVE LOGITS
    ↵
    3.27
     is
    3.00
    ），
    2.56
    e
    2.38
    .
    2.23
    ge
    2.22
     $
    2.19
     "
    2.14
     et
    2.11
    </h4>
    2.06
    Activations Density 0.007%

    No Known Activations