© 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. 8212
    Prev
    Next
    INDEX
    Explanations

    production

    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
    埽
    -3.53
    镦
    -3.11
    栊
    -2.98
    硨
    -2.88
    秾
    -2.67
     restoran
    -2.56
     стал
    -2.53
    because
    -2.52
    also
    -2.45
    颜色
    -2.45
    POSITIVE LOGITS
    摇了
    3.50
     We
    3.31
    瑨
    3.28
    ญี่ป
    3.09
    獃
    2.86
    o
    2.75
    摭
    2.67
    锝
    2.50
     wiele
    2.50
     Now
    2.47
    Activations Density 0.049%

    No Known Activations