© 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. 41889
    Prev
    Next
    INDEX
    Explanations

    local people, places, and groups

    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
     that
    -1.95
    There
    -1.60
     other
    -1.51
     there
    -1.48
     you
    -1.36
     up
    -1.34
     where
    -1.30
     Çünkü
    -1.28
     Lainnya
    -1.23
     with
    -1.22
    POSITIVE LOGITS
     Memoriam
    1.49
     البرنامج
    1.48
    cognito
    1.37
     серый
    1.37
     beider
    1.36
     __
    1.32
    膊
    1.32
     einsch
    1.29
    ="#"><
    1.28
     OREGON
    1.28
    Activations Density 0.019%

    No Known Activations