© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67965
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and code identifiers

    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
     menjual
    -0.97
     ortaya
    -0.96
     desnuda
    -0.93
    sius
    -0.88
    RemoveAll
    -0.86
    dymo
    -0.86
    inio
    -0.85
     tromper
    -0.85
    getTitle
    -0.85
    entown
    -0.84
    POSITIVE LOGITS
     his
    0.91
     [
    0.90
    getID
    0.83
     (
    0.82
    ctober
    0.81
     ২০১
    0.80
     His
    0.79
     堀
    0.77
    CompilerServices
    0.77
     objectively
    0.75
    Activations Density 0.004%

    No Known Activations