© 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. 27632
    Prev
    Next
    INDEX
    Explanations

    was described

    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
     three
    -1.80
     will
    -1.73
     four
    -1.73
     with
    -1.67
     two
    -1.65
     at
    -1.62
     variedades
    -1.55
     would
    -1.51
     five
    -1.51
     eight
    -1.48
    POSITIVE LOGITS
     europé
    1.47
     pesso
    1.42
     keten
    1.41
     frança
    1.41
    湳
    1.39
     lørdag
    1.38
     esteve
    1.35
    べく
    1.34
     didn
    1.30
     alho
    1.30
    Activations Density 0.049%

    No Known Activations