© 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. 8438
    Prev
    Next
    INDEX
    Explanations

    our or which

    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
     mereka
    -1.49
     is
    -1.37
     Futebol
    -1.23
     &
    -1.23
     elas
    -1.22
    '
    -1.20
    かつ
    -1.18
     of
    -1.18
     asegurarse
    -1.18
    茌
    -1.16
    POSITIVE LOGITS
     which
    1.69
     Какие
    1.58
     our
    1.56
     your
    1.55
     Какой
    1.49
    lana
    1.48
    nade
    1.45
     första
    1.43
    unno
    1.38
     efekt
    1.38
    Activations Density 0.127%

    No Known Activations