© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5785
    Prev
    Next
    INDEX
    Explanations

    code documentation

    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
     तभी
    0.62
     ряд
    0.61
    erms
    0.61
     strokes
    0.60
    団
    0.59
    endo
    0.59
    сной
    0.58
     scr
    0.58
    ③
    0.58
    ([
    0.56
    POSITIVE LOGITS
     ז
    0.79
     تريد
    0.76
    ەل
    0.76
     Telev
    0.74
     ز
    0.74
     televisão
    0.73
     طا
    0.72
    стера
    0.72
     Workplace
    0.71
    টেন
    0.70
    Activations Density 0.028%

    No Known Activations