© 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. 7066
    Prev
    Next
    INDEX
    Explanations

    enzyme linked

    np_acts-logits-general · gemini-2.5-flash-lite

    human-like conversation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     円
    0.56
     Дет
    0.52
    setTime
    0.50
     antiquity
    0.50
    ર્ક
    0.50
     CXCL
    0.49
     Че
    0.49
     старо
    0.47
     Ак
    0.47
     millennia
    0.47
    POSITIVE LOGITS
    的文件
    0.50
     dezelfde
    0.46
     mayoría
    0.45
    CLA
    0.44
     integr
    0.42
    $...
    0.42
    >(
    0.42
    的产品
    0.41
     větš
    0.41
    StaticHandler
    0.41
    Activations Density 0.000%

    No Known Activations