© 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. 16481
    Prev
    Next
    INDEX
    Explanations

    list separators

    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
    hehehe
    -1.33
    えっ
    -1.27
     Puedes
    -1.24
    ĭ
    -1.24
     disponibilités
    -1.21
     Muchos
    -1.20
    来週
    -1.19
    我が家
    -1.18
    FFECT
    -1.18
    necessarily
    -1.17
    POSITIVE LOGITS
     as
    1.31
     to
    1.27
     using
    1.23
     so
    1.19
     from
    1.17
     uses
    1.09
     use
    1.01
     re
    1.01
     goes
    1.01
     begin
    1.00
    Activations Density 0.016%

    No Known Activations