© 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. 64575
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming punctuation

    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
     of
    -1.47
     to
    -1.41
     by
    -1.28
     (
    -1.25
    皺
    -1.18
     алюми
    -1.15
    copus
    -1.09
    PasswordEncoder
    -1.09
    ''');
    -1.09
     трубы
    -1.08
    POSITIVE LOGITS
     afspraak
    1.21
     divertimento
    1.17
     sottile
    1.13
    蕯
    1.09
    enumer
    1.09
    Zitat
    1.09
     soddis
    1.08
     tuviera
    1.07
     باسلام
    1.07
     conosco
    1.07
    Activations Density 0.001%

    No Known Activations