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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93429
    Prev
    Next
    INDEX
    Explanations

    java imports and classes

    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
    .
    -1.45
     it
    -1.37
     needed
    -1.27
     also
    -1.27
     ...
    -1.18
     H
    -1.14
    '
    -1.14
     <
    -1.14
     all
    -1.11
     join
    -1.10
    POSITIVE LOGITS
    Lø
    1.55
     rencontr
    1.49
    Cevap
    1.47
    Recept
    1.45
    سوال
    1.41
     використовувати
    1.41
    Zdrav
    1.35
    Farbe
    1.34
    Komentar
    1.33
     triko
    1.32
    Activations Density 0.012%

    No Known Activations