© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92917
    Prev
    Next
    INDEX
    Explanations

    variable declarations

    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_34/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
     célè
    -2.31
     parfüm
    -2.25
     剧照
    -2.19
    gebraucht
    -2.16
     verschillende
    -2.16
     rése
    -2.14
     bluz
    -2.14
    麃
    -2.08
     fidé
    -2.08
     parfü
    -2.05
    POSITIVE LOGITS
     in
    2.64
     (
    2.41
     is
    2.22
     at
    2.14
     
    2.09
     now
    2.08
     on
    2.03
     $
    1.95
     M
    1.88
     as
    1.87
    Activations Density 0.037%

    No Known Activations