© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66784
    Prev
    Next
    INDEX
    Explanations

    Hend and Humphrey names

    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
     tetapi
    -3.31
    ."
    -2.70
     所以
    -2.67
    '
    -2.64
    e
    -2.61
    </strong>
    -2.55
    1
    -2.45
     gän
    -2.41
    </u>
    -2.39
     целей
    -2.38
    POSITIVE LOGITS
     邊
    2.72
     яка
    2.69
    
    2.59
    鿬
    2.42
    絰
    2.41
     輕
    2.39
    ﾝ
    2.39
     公园
    2.38
     复古
    2.38
    ments
    2.38
    Activations Density 0.002%

    No Known Activations