© 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. 58421
    Prev
    Next
    INDEX
    Explanations

    quantities and extent

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

    non-english words and phrases

    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
    ۱
    0.62
     ۱
    0.55
    :$
    0.54
    ۷
    0.53
    ۶
    0.52
    $
    0.48
    ۲
    0.48
    ۵
    0.48
    タグ
    0.47
     $
    0.46
    POSITIVE LOGITS
    ქვენ
    0.46
     você
    0.45
     сложно
    0.45
     comrades
    0.44
     denke
    0.44
     বজ্র
    0.44
     colegas
    0.44
    ્યાં
    0.43
     coraz
    0.43
    ají
    0.43
    Activations Density 0.000%

    No Known Activations