© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 53922
    Prev
    Next
    INDEX
    Explanations

    translate individual sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    說明
    0.46
     बदलना
    0.45
    ро
    0.43
     なさい
    0.43
    郤
    0.42
    цыя
    0.42
     คุณ
    0.42
    錢
    0.42
    钱
    0.42
    蓁
    0.42
    POSITIVE LOGITS
     in
    0.44
     epoch
    0.41
     continues
    0.41
     gibt
    0.41
     första
    0.40
     först
    0.40
     første
    0.39
     interpret
    0.39
     epochs
    0.39
     intersects
    0.39
    Activations Density 0.005%

    No Known Activations