© 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. 12734
    Prev
    Next
    INDEX
    Explanations

    sup.x, sup.1+

    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
     when
    -2.22
     in
    -2.13
     then
    -1.91
     which
    -1.82
     if
    -1.75
     providing
    -1.73
     before
    -1.70
     конкурс
    -1.70
     службу
    -1.70
    我没
    -1.70
    POSITIVE LOGITS
    ’
    2.31
     ก็
    1.95
     ་
    1.85
     zustand
    1.77
     geringe
    1.73
    岽
    1.73
    '
    1.70
     normalement
    1.68
    伋
    1.66
     เป็น
    1.63
    Activations Density 0.000%

    No Known Activations