© 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. 43402
    Prev
    Next
    INDEX
    Explanations

    copyright owner

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

    copyright notice

    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
     marinated
    0.46
    が多い
    0.46
    𓍊
    0.44
     ০১
    0.43
    ใจ
    0.42
     akhir
    0.42
    大数据
    0.42
     формате
    0.42
    ೇನೆ
    0.41
    اقی
    0.40
    POSITIVE LOGITS
    t
    0.51
    name
    0.46
    c
    0.44
    th
    0.43
    kh
    0.43
    称号
    0.41
    cL
    0.40
     Bes
    0.39
     и
    0.39
     Entonces
    0.39
    Activations Density 0.000%

    No Known Activations