© 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. 195938
    Prev
    Next
    INDEX
    Explanations

    deter witches, these formal, dinosaur fossils

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

    `. , path creates distribution

    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
    ণি
    0.51
    根
    0.49
    Cartoon
    0.49
     freezer
    0.47
     affiliation
    0.47
     humble
    0.47
     Canyon
    0.46
     canyon
    0.46
    ↵↵
    0.45
    柳
    0.45
    POSITIVE LOGITS
     אנ
    0.50
     ډاونلوډ
    0.50
     समानार्थी
    0.48
     عامل
    0.48
    óch
    0.48
    <unused665>
    0.47
     صعبه
    0.47
    <unused200>
    0.47
    <unused511>
    0.46
    ویں
    0.46
    Activations Density 0.012%

    No Known Activations