© 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. 25204
    Prev
    Next
    INDEX
    Explanations

    only followed by qualifier

    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
    Not in Any Lists

    No Comments

    Negative Logits
    venant
    -1.18
    を変更
    -1.16
     need
    -1.12
    ふり
    -1.09
    がありません
    -1.07
    Makan
    -1.07
     even
    -1.07
    はなく
    -1.05
     procra
    -1.05
     面包
    -1.05
    POSITIVE LOGITS
     by
    1.39
     with
    1.36
     mieście
    1.14
     Mungkin
    1.02
     cierta
    1.01
     Lakukan
    1.00
     AFTER
    0.99
    ৢ
    0.98
     result
    0.96
    utah
    0.95
    Activations Density 0.023%

    No Known Activations