© 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. 99367
    Prev
    Next
    INDEX
    Explanations

    but also

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

    AI integration

    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
    ل
    0.45
    ギュア
    0.45
    屍
    0.45
    ין
    0.45
    behör
    0.44
    他們
    0.43
    뱀
    0.43
    墳
    0.42
    ława
    0.42
    iš
    0.41
    POSITIVE LOGITS
     Pittsburgh
    0.50
     khấu
    0.50
     Oatmeal
    0.47
     Allegheny
    0.45
    🥸
    0.45
     Leipzig
    0.45
     Ukrainians
    0.44
     ahu
    0.44
     Kiev
    0.44
     trở
    0.43
    Activations Density 0.001%

    No Known Activations