© 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. 40490
    Prev
    Next
    INDEX
    Explanations

    well, with, he, the

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

    lists and items

    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
    وي
    0.51
     الم
    0.49
    蘆
    0.49
    لي
    0.49
    та
    0.46
    ية
    0.46
     பதில
    0.45
    وية
    0.44
     سبيل
    0.44
    роб
    0.43
    POSITIVE LOGITS
    yscy
    0.51
     perasaan
    0.49
     explor
    0.46
    FTWARE
    0.45
    DZ
    0.45
     TM
    0.45
     آهنگ
    0.44
     menonton
    0.43
     автором
    0.43
    儚
    0.43
    Activations Density 0.000%

    No Known Activations