© 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. 67982
    Prev
    Next
    INDEX
    Explanations

    yoga sessions, journey, and basics

    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
    瑨
    -2.83
    zość
    -2.66
    稣
    -2.53
    訁
    -2.53
    á
    -2.48
    
    -2.41
    gées
    -2.39
     is
    -2.28
    餍
    -2.27
    鴴
    -2.27
    POSITIVE LOGITS
    The
    2.64
    There
    2.39
    邂
    2.36
    𖣘
    2.30
    媖
    2.27
    They
    2.23
    铤
    2.23
    ዡ
    2.22
    鉭
    2.19
     fantástica
    2.16
    Activations Density 0.006%

    No Known Activations