© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16050
    Prev
    Next
    INDEX
    Explanations

    code comments and structure definitions

    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
    ֶּ
    -1.44
     бампер
    -1.42
    ַּ
    -1.38
    ִּ
    -1.36
     ベビー
    -1.29
    Zna
    -1.27
    🏟
    -1.23
    Komentar
    -1.20
     yrs
    -1.18
    ICIOS
    -1.17
    POSITIVE LOGITS
    谥
    1.59
    謚
    1.18
     cristianos
    1.18
     seems
    1.15
    諡
    1.13
     something
    1.12
     there
    1.11
     capacidades
    1.09
     яйцо
    1.09
     chré
    1.09
    Activations Density 0.016%

    No Known Activations