© 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. 10-GEMMASCOPE-RES-131K
    7. 101562
    Prev
    Next
    INDEX
    Explanations

    author citations

    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
    킁
    -2.23
    粜
    -2.22
    
    -2.11
    𓁹
    -2.08
     ส์
    -2.08
     viſ
    -2.00
     exhilarating
    -1.99
     Dinas
    -1.95
    摀
    -1.92
    桖
    -1.91
    POSITIVE LOGITS
     Since
    2.69
     new
    2.45
     Because
    2.22
     For
    2.22
     because
    2.19
     reduces
    2.17
     Despite
    2.13
     Taking
    2.06
     There
    2.03
     From
    2.03
    Activations Density 0.056%

    No Known Activations