© 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. 60158
    Prev
    Next
    INDEX
    Explanations

    country or nation

    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
    '
    -1.77
    大爷
    -1.53
    おすすめの
    -1.51
    入荷
    -1.47
    前辈
    -1.45
    很赞
    -1.43
    の存在
    -1.42
    挑选
    -1.42
     SIZES
    -1.41
    ストール
    -1.37
    POSITIVE LOGITS
    」「
    1.78
    this
    1.70
    you
    1.66
    You
    1.62
     ‘’
    1.60
     ۲۵
    1.59
    ')):
    1.57
    urious
    1.57
    reated
    1.54
     ۶
    1.52
    Activations Density 0.010%

    No Known Activations