© 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. 9959
    Prev
    Next
    INDEX
    Explanations

    start of a question

    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
     =
    -2.02
    鴣
    -1.95
     of
    -1.91
     souligné
    -1.85
     has
    -1.81
    s
    -1.78
     or
    -1.70
     triliun
    -1.66
     utter
    -1.66
     to
    -1.63
    POSITIVE LOGITS
    鹟
    2.78
    ჻
    2.42
    ,..
    2.33
    maybe
    2.05
    might
    2.03
    盌
    2.03
    奩
    2.02
    perhaps
    1.98
    沵
    1.97
    肏
    1.95
    Activations Density 0.001%

    No Known Activations