© 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. 51445
    Prev
    Next
    INDEX
    Explanations

    using stdio

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

    using namespace

    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
     আতঙ্ক
    0.51
    rolled
    0.50
    indexes
    0.48
     حساس
    0.48
    ]-\
    0.47
    あと
    0.47
     inizi
    0.46
    ⑮
    0.46
    waterslide
    0.46
    ometers
    0.45
    POSITIVE LOGITS
     ऐसा
    0.54
    假
    0.47
     पूछा
    0.42
     कहा
    0.42
     болу
    0.40
     就
    0.40
    彤
    0.40
     வடிவ
    0.39
     ऐसी
    0.39
     फर्जी
    0.38
    Activations Density 0.000%

    No Known Activations