© 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. 161247
    Prev
    Next
    INDEX
    Explanations

    bound books

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

    program, resource, division

    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
    醀
    0.50
    聝
    0.49
    EW
    0.48
     पूर्ति
    0.48
     ഉത്തര
    0.48
    牷
    0.48
     dow
    0.47
    ళ్ళ
    0.47
    indexBuffer
    0.46
     inns
    0.46
    POSITIVE LOGITS
    ையில்
    0.47
    ния
    0.43
    დნენ
    0.41
    ᧐
    0.41
    یر
    0.40
     Albums
    0.39
    met
    0.39
    看不到
    0.39
    sust
    0.39
    ukes
    0.39
    Activations Density 0.000%

    No Known Activations