© 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. 67769
    Prev
    Next
    INDEX
    Explanations

    good cop, good people, good science, Good Friday

    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
    罴
    -3.25
     "
    -2.86
    臜
    -2.84
    皤
    -2.80
    晢
    -2.72
    跸
    -2.72
    鸲
    -2.72
     dritte
    -2.70
     superstar
    -2.67
    ⍢
    -2.63
    POSITIVE LOGITS
    鉆
    2.80
     However
    2.73
     Also
    2.56
     atau
    2.50
    或者
    2.44
     Surprisingly
    2.41
     ヶ
    2.39
    菈
    2.38
    However
    2.31
    あります
    2.31
    Activations Density 0.032%

    No Known Activations