© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1970
    Prev
    Next
    INDEX
    Explanations

    end-to-end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_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
     காமெ
    0.61
     comb
    0.60
    ಗ್ಗೆ
    0.57
     stiff
    0.56
     ج
    0.55
     J
    0.55
     receita
    0.54
     Déf
    0.54
     kindness
    0.54
    ades
    0.54
    POSITIVE LOGITS
    TO
    0.68
    to
    0.66
    til
    0.64
    uper
    0.63
    bym
    0.63
    분을
    0.63
    IL
    0.61
    文字
    0.61
    To
    0.61
    俺
    0.60
    Activations Density 0.312%

    No Known Activations