© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40051
    Prev
    Next
    INDEX
    Explanations

    hex color codes

    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
    on
    -3.28
    a
    -3.27
    ing
    -2.64
     alltså
    -2.63
     särskilt
    -2.39
    s
    -2.36
    With
    -2.22
     如
    -2.19
    Of
    -2.14
    it
    -2.13
    POSITIVE LOGITS
    Ꭳ
    2.67
     planètes
    2.66
    螄
    2.58
    賅
    2.53
     the
    2.50
    
    2.47
    }\
    2.39
    窳
    2.34
     attaques
    2.31
    尪
    2.31
    Activations Density 0.006%

    No Known Activations