© 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. 39638
    Prev
    Next
    INDEX
    Explanations

    sports teams and bands

    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
    女
    -2.66
    齷
    -2.64
    馘
    -2.63
    蔸
    -2.59
    蟊
    -2.58
    薆
    -2.56
     abus
    -2.52
    甞
    -2.45
     effets
    -2.42
    opportunities
    -2.39
    POSITIVE LOGITS
    ing
    3.58
    3.55
    	
    3.52
    2
    3.22
    汌
    2.98
            
    2.75
     llamado
    2.63
    í
    2.59
    甚至是
    2.56
    Of
    2.55
    Activations Density 0.005%
    No Known Activations