© 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. 1324
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
    鶿
    -3.42
    ꦫ
    -3.11
    
    -2.92
    紲
    -2.92
     juſ
    -2.83
    ⛦
    -2.78
    ⽌
    -2.78
    檍
    -2.72
    甞
    -2.64
    ⁛
    -2.64
    POSITIVE LOGITS
    [
    2.92
     for
    2.89
     What
    2.75
     allows
    2.55
     gives
    2.53
    From
    2.52
     but
    2.50
     has
    2.47
     From
    2.45
    as
    2.44
    Activations Density 0.019%

    No Known Activations