© 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. 70087
    Prev
    Next
    INDEX
    Explanations

    tried and true

    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
     for
    -3.42
     to
    -3.13
     in
    -3.06
     by
    -2.97
     most
    -2.56
     at
    -2.39
     from
    -2.36
     during
    -2.34
     after
    -2.34
     has
    -2.31
    POSITIVE LOGITS
     régal
    2.22
     corriger
    2.22
    Här
    2.19
     parfü
    2.19
     enthou
    2.17
    Setiap
    2.08
    茈
    2.08
     arrêter
    2.08
     rafraî
    2.06
     éviter
    2.05
    Activations Density 0.265%

    No Known Activations