© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2046
    Prev
    Next
    INDEX
    Explanations

    multilingual commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_16k_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
     zar
    0.65
     cap
    0.64
     house
    0.60
     Gan
    0.59
    鬟
    0.58
     AGEN
    0.57
    ကြား
    0.57
    angas
    0.56
    ranged
    0.56
    랜
    0.56
    POSITIVE LOGITS
    command
    0.74
     command
    0.73
     Command
    0.73
    ارق
    0.69
    Command
    0.66
    таль
    0.64
     காமெ
    0.64
    コマンド
    0.63
     perintah
    0.62
     conformal
    0.62
    Activations Density 0.369%

    No Known Activations