© 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. 22-GEMMASCOPE-RES-131K
    7. 33522
    Prev
    Next
    INDEX
    Explanations

    list items and formatting

    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_22/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
     of
    -1.73
     uses
    -1.29
     This
    -1.21
     When
    -1.19
     makes
    -1.17
     use
    -1.13
     on
    -1.11
     незавер
    -1.09
    》、《
    -1.09
     provide
    -1.09
    POSITIVE LOGITS
     burbuja
    1.21
     czter
    1.14
     dwóch
    1.14
    ඞ
    1.14
    ウール
    1.13
    aceite
    1.13
     Dinas
    1.13
     ,'
    1.13
     kinda
    1.12
     quirúrg
    1.12
    Activations Density 0.089%

    No Known Activations