© 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. 134079
    Prev
    Next
    INDEX
    Explanations

    starting a category/context

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

    for (what)

    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
     ຮ
    0.50
     enfermed
    0.49
     পর্যবেক্ষণ
    0.48
     ভিত
    0.48
     thất
    0.48
     ଯ
    0.47
    काम
    0.46
     manière
    0.46
     motorcycles
    0.45
    IENT
    0.45
    POSITIVE LOGITS
    തി
    0.50
    t
    0.50
     Touching
    0.49
    ارہ
    0.46
    petition
    0.46
     Appear
    0.45
     Optimal
    0.44
    tych
    0.44
    defining
    0.44
    出现
    0.43
    Activations Density 0.000%

    No Known Activations