© 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. 151493
    Prev
    Next
    INDEX
    Explanations

    accepts applications

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

    controlled areas

    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
    stu
    0.47
    事情
    0.46
    事
    0.46
    ac
    0.45
    machine
    0.45
    粘贴
    0.43
    w
    0.43
    による
    0.42
     الفصل
    0.42
    zen
    0.42
    POSITIVE LOGITS
     widows
    0.52
     বিস্ফ
    0.50
     Widow
    0.47
     Mayfield
    0.46
     Parks
    0.46
    াহরণ
    0.46
     Moms
    0.46
     Wid
    0.46
     $=\
    0.46
    ạn
    0.45
    Activations Density 0.000%

    No Known Activations