© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35438
    Prev
    Next
    INDEX
    Explanations

    art and posters

    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
    ּוֹ
    -1.73
    ִּ
    -1.61
     dépenses
    -1.47
     coelho
    -1.43
    ַּ
    -1.42
     investissements
    -1.41
     ">
    -1.38
    ֶּ
    -1.38
     who
    -1.38
     entusias
    -1.36
    POSITIVE LOGITS
     with
    2.09
     from
    1.91
     after
    1.71
    ׇ
    1.60
     at
    1.60
     on
    1.57
     in
    1.56
     during
    1.43
     showing
    1.42
     without
    1.40
    Activations Density 0.018%

    No Known Activations