© 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. 22-GEMMASCOPE-RES-131K
    7. 33459
    Prev
    Next
    INDEX
    Explanations

    sports leagues and teams

    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_22/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
    गा
    -0.99
    mrow
    -0.97
    ˏ
    -0.97
     prostředí
    -0.97
     elapsed
    -0.90
    หัว
    -0.88
     juara
    -0.87
     réglage
    -0.87
     hitter
    -0.86
    stuhl
    -0.85
    POSITIVE LOGITS
     mainstream
    0.97
     rejection
    0.88
    บ้าง
    0.84
    rook
    0.82
     junior
    0.80
    พ์
    0.79
    filtering
    0.79
     monitoring
    0.78
    是小
    0.77
    σιμοποι
    0.76
    Activations Density 0.143%

    No Known Activations