© 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. 72375
    Prev
    Next
    INDEX
    Explanations

    Kobe, McLaren, Vuitton

    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
    ꯸
    -2.72
    结语
    -2.72
    
    -2.45
    手绘
    -2.36
    􀂃
    -2.30
    ဴ
    -2.28
    𖤣
    -2.28
    媜
    -2.27
    古风
    -2.27
    性別
    -2.25
    POSITIVE LOGITS
    да
    2.61
    .
    2.47
    ↵↵
    2.39
    and
    2.38
    "
    2.27
     tutte
    2.13
     várias
    2.13
     tion
    2.08
    鶫
    2.05
     oft
    2.03
    Activations Density 0.003%

    No Known Activations