© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130064
    Prev
    Next
    INDEX
    Explanations

    self- words

    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
     pericolo
    -1.42
     WOMAN
    -1.41
     affez
    -1.37
    '));
    -1.33
    ;
    -1.29
     sebelumnya
    -1.29
     zamiast
    -1.28
    ToSave
    -1.27
    ',
    -1.27
    cije
    -1.27
    POSITIVE LOGITS
     r
    1.37
     F
    1.34
     D
    1.31
     U
    1.29
     B
    1.28
     "
    1.27
     as
    1.27
     not
    1.27
    That
    1.26
    ichtete
    1.25
    Activations Density 0.093%

    No Known Activations