© 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. 68616
    Prev
    Next
    INDEX
    Explanations

    verification and account recovery

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

    updates thecalculates thevulnerable to

    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
    H
    0.50
    राबरी
    0.49
    ड
    0.48
    Vu
    0.47
    クリ
    0.47
     sufficiency
    0.47
    エ
    0.46
     denunci
    0.46
    Ha
    0.46
    Bott
    0.46
    POSITIVE LOGITS
    eonium
    0.52
     المصفوف
    0.51
    overline
    0.51
     পরিষদ
    0.50
     கேரள
    0.49
     রামগতি
    0.48
    ="<%=
    0.48
    啵
    0.47
     ट्यूब
    0.46
     获取
    0.46
    Activations Density 0.000%

    No Known Activations