© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6848
    Prev
    Next
    INDEX
    Explanations

    " or "

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_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
    基础
    0.33
     কারও
    0.33
     দুইটি
    0.31
     এখনও
    0.30
     ಏನು
    0.28
     The
    0.28
     चौकी
    0.28
    ट
    0.27
     কখনও
    0.27
     বিষয়ে
    0.27
    POSITIVE LOGITS
    ‼
    0.38
    ਫ
    0.35
    spirational
    0.30
    imde
    0.29
    ycz
    0.28
    cohols
    0.28
    ivores
    0.28
    НО
    0.28
     др
    0.27
    olari
    0.27
    Activations Density 2.455%

    No Known Activations