© 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. 9438
    Prev
    Next
    INDEX
    Explanations

    Mach names

    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
     with
    -3.84
     at
    -3.30
     on
    -2.94
     in
    -2.91
     by
    -2.88
     for
    -2.80
     until
    -2.70
     through
    -2.45
     under
    -2.45
     without
    -2.44
    POSITIVE LOGITS
     régal
    2.23
    硨
    2.22
     refroid
    2.16
     corriger
    2.14
     créer
    2.11
     relâche
    2.09
    蓠
    2.09
     rafraî
    2.08
     '"
    2.05
     bascul
    2.05
    Activations Density 1.890%

    No Known Activations