© 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. 13069
    Prev
    Next
    INDEX
    Explanations

    some ofkind ofsort of

    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
     judicia
    -1.05
     פֿ
    -1.02
     összefoglal
    -1.01
    腠
    -1.00
    就把
    -0.98
     pamamagitan
    -0.98
    ssymb
    -0.98
     actuellement
    -0.97
    okra
    -0.97
    숟
    -0.97
    POSITIVE LOGITS
     either
    3.83
    either
    2.92
    Either
    2.70
     entweder
    2.50
     or
    2.50
     либо
    2.45
     Either
    2.31
     alguna
    2.09
     algún
    1.94
    要么
    1.92
    Activations Density 0.068%

    No Known Activations