© 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. 39867
    Prev
    Next
    INDEX
    Explanations

    athletics administration championships

    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
    媃
    -2.86
    ！"
    -2.59
    嫱
    -2.48
    When
    -2.48
    佧
    -2.39
    Once
    -2.33
    寕
    -2.33
     端
    -2.33
    تیجه
    -2.30
     tayang
    -2.22
    POSITIVE LOGITS
    d
    3.81
    e
    3.20
    r
    2.98
    )$
    2.72
    m
    2.70
    鍆
    2.67
    b
    2.67
    焄
    2.64
     saiba
    2.58
     черная
    2.48
    Activations Density 0.003%

    No Known Activations