© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75276
    Prev
    Next
    INDEX
    Explanations

    curly braces; Jinja2, regex patterns

    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
     nové
    -0.90
     so
    -0.90
     samym
    -0.83
    ativeness
    -0.82
    椅
    -0.80
     así
    -0.79
     kiedy
    -0.78
    Notes
    -0.78
     supaya
    -0.78
    ciente
    -0.78
    POSITIVE LOGITS
     then
    1.22
     followed
    1.04
     Estoy
    0.95
    ∐
    0.90
     petto
    0.85
     armat
    0.84
     everything
    0.84
     INCOR
    0.82
     speedo
    0.82
     سپس
    0.81
    Activations Density 0.028%

    No Known Activations