© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3479
    Prev
    Next
    INDEX
    Explanations

    na, на, på, auf

    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_65k_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
     Tại
    0.68
     وابسته
    0.64
    ješt
    0.61
    에서
    0.60
    많
    0.60
     बदल
    0.60
     Wahr
    0.59
     많
    0.59
    變
    0.59
     kapsamında
    0.59
    POSITIVE LOGITS
     einen
    0.65
     sin
    0.57
     richtigen
    0.56
     den
    0.56
    まった
    0.53
     jedem
    0.52
     자기
    0.52
     sebe
    0.52
    ോള
    0.50
    cione
    0.50
    Activations Density 0.018%

    No Known Activations