© 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. 10-GEMMASCOPE-RES-131K
    7. 71024
    Prev
    Next
    INDEX
    Explanations

    the adjective noun

    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
     ścian
    -1.48
     quando
    -1.45
     diversité
    -1.38
     When
    -1.30
     the
    -1.27
     cuando
    -1.27
     have
    -1.26
    虽然
    -1.25
     lorsqu
    -1.25
    ahuje
    -1.23
    POSITIVE LOGITS
     to
    1.95
     in
    1.66
    潦
    1.38
     on
    1.26
    事了
    1.23
     хотел
    1.23
     then
    1.19
     at
    1.19
    قات
    1.19
     meisje
    1.18
    Activations Density 0.042%

    No Known Activations