© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100219
    Prev
    Next
    INDEX
    Explanations

    football clubs and managers

    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
    ↵
    -2.77
    (
    -2.33
    )
    -1.99
    ,’
    -1.85
    是一个
    -1.76
     there
    -1.64
    ꒥
    -1.56
    ( ̄
    -1.52
     japones
    -1.52
     rigue
    -1.49
    POSITIVE LOGITS
    勦
    1.97
    ates
    1.67
    for
    1.66
    硨
    1.65
    𝙜
    1.63
     }));
    1.57
    楽しんで
    1.53
     $^{\
    1.50
    地在
    1.50
    IntentFilter
    1.49
    Activations Density 0.007%

    No Known Activations