© 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. 71829
    Prev
    Next
    INDEX
    Explanations

    during an action

    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
    อื่น
    -2.86
    戗
    -2.75
    絝
    -2.61
    ⾒
    -2.58
     divertidas
    -2.58
    蛧
    -2.56
    程度上
    -2.56
     tranquila
    -2.53
     preocupado
    -2.53
    颇
    -2.50
    POSITIVE LOGITS
    ي
    3.69
    0
    3.11
    是什麼
    3.03
    *
    2.98
    i
    2.72
    瘩
    2.70
    that
    2.69
    י
    2.66
     Houſe
    2.64
    褔
    2.56
    Activations Density 0.045%

    No Known Activations