© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 257561
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    is
    0.49
    在
    0.45
     మరింత
    0.45
    isDebug
    0.45
    时间
    0.43
    pg
    0.43
    nto
    0.43
    са
    0.42
    isIn
    0.42
    辏
    0.42
    POSITIVE LOGITS
     mu
    0.50
     kunst
    0.49
     cult
    0.48
     Muj
    0.48
    ੍ਹਾਂ
    0.47
     potrav
    0.47
     viet
    0.47
     deaths
    0.46
     servidor
    0.46
     apari
    0.46
    Activations Density 0.001%

    No Known Activations