© 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. 22-GEMMASCOPE-RES-131K
    7. 35173
    Prev
    Next
    INDEX
    Explanations

    phys rev journal citations

    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
     until
    -1.49
    越是
    -1.48
     about
    -1.45
     verur
    -1.45
     that
    -1.42
    ;
    -1.41
    づけ
    -1.40
     fueron
    -1.40
     Persön
    -1.39
     mejorando
    -1.38
    POSITIVE LOGITS
     vader
    1.80
     taal
    1.73
     vider
    1.73
     yng
    1.67
     dage
    1.66
     aya
    1.57
     guz
    1.57
     hiver
    1.57
     engels
    1.56
    蚰
    1.56
    Activations Density 0.001%

    No Known Activations