© 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. 86245
    Prev
    Next
    INDEX
    Explanations

    most effective

    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
     noiva
    -1.66
     {
    -1.54
    实话
    -1.48
     huellas
    -1.48
    っております
    -1.48
     mismas
    -1.48
    なかなか
    -1.45
     irmã
    -1.45
    鯪
    -1.42
     sereia
    -1.39
    POSITIVE LOGITS
    p
    1.52
     nuovi
    1.45
     nieuwe
    1.37
    c
    1.32
    v
    1.31
     or
    1.29
     kveld
    1.28
    b
    1.28
    or
    1.27
    ケット
    1.27
    Activations Density 0.007%

    No Known Activations