© 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. 64805
    Prev
    Next
    INDEX
    Explanations

    audience participation

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

    from, finding

    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
     aria
    0.53
    p
    0.50
     mia
    0.48
    d
    0.48
    uva
    0.47
    cut
    0.45
     lux
    0.44
     luxe
    0.44
    ingi
    0.43
    fox
    0.43
    POSITIVE LOGITS
     Nhưng
    0.46
     Hän
    0.45
     undertakes
    0.44
     سنگ
    0.44
     Ø
    0.43
     يسم
    0.42
     Ё
    0.42
    档案馆
    0.42
     Shandong
    0.41
     Trucks
    0.41
    Activations Density 0.000%

    No Known Activations