© 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. 200348
    Prev
    Next
    INDEX
    Explanations

    question/answer prompts

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

    curious aboutwriting something

    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
    V
    0.60
    N
    0.55
    S
    0.52
    o
    0.48
    ین
    0.47
    G
    0.47
    J
    0.46
    Z
    0.45
    W
    0.45
     Notably
    0.44
    POSITIVE LOGITS
     Лей
    0.52
     ас
    0.49
     здания
    0.49
     dạy
    0.46
    pleri
    0.46
    便于
    0.46
     अतिक
    0.46
     आदेश
    0.46
     актив
    0.45
     भेज
    0.45
    Activations Density 0.001%

    No Known Activations