© 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. 22500
    Prev
    Next
    INDEX
    Explanations

    technical or contextual introductions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    땃
    -2.56
    罍
    -2.55
    鸸
    -2.52
    蟊
    -2.47
    牁
    -2.44
    嫑
    -2.41
     rafra
    -2.38
    𓋼
    -2.38
     parut
    -2.36
    錾
    -2.36
    POSITIVE LOGITS
    '
    2.73
    ’
    2.63
     
    2.48
    ）
    2.47
    c
    2.41
    </strong>
    2.34
    。
    2.34
    “
    2.31
    …”
    2.23
    f
    2.23
    Activations Density 0.001%

    No Known Activations