© 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. 10-GEMMASCOPE-RES-131K
    7. 105950
    Prev
    Next
    INDEX
    Explanations

    fields of work or society

    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_10/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
     culte
    -1.32
     also
    -1.23
     również
    -1.19
    ﺯ
    -1.19
     parfüm
    -1.18
     plancher
    -1.16
     akku
    -1.14
     öv
    -1.14
     which
    -1.11
    Život
    -1.10
    POSITIVE LOGITS
     their
    1.39
    </strong>
    1.38
     as
    1.27
    chiat
    1.12
     только
    1.05
    躂
    1.04
    VIDEO
    1.03
     beträgt
    1.02
     a
    1.02
     Werken
    1.01
    Activations Density 0.091%

    No Known Activations