© 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. 16413
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    ม่
    -1.20
    ള്
    -1.18
    还想
    -1.16
     mohou
    -1.13
    phorus
    -1.13
     尔
    -1.11
     hinges
    -1.09
     姆
    -1.09
    end
    -1.09
    }\
    -1.07
    POSITIVE LOGITS
     turist
    1.22
     ganti
    1.15
     statistik
    1.14
     eksklu
    1.14
     casque
    1.14
     mikrofon
    1.14
     rekla
    1.11
     deklar
    1.11
    pizza
    1.11
     buk
    1.09
    Activations Density 0.070%

    No Known Activations