© 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. 6810
    Prev
    Next
    INDEX
    Explanations

    dash it all, flash cards, cash

    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
    蜱
    0.72
     মাধ্য
    0.61
    дцать
    0.61
    电视
    0.58
     szy
    0.57
     affirmat
    0.57
    সময়
    0.56
    ዚያ
    0.55
    关键词
    0.55
    els
    0.55
    POSITIVE LOGITS
    ׂ
    1.00
    ׁ
    0.71
    warz
    0.69
    hhhh
    0.67
    hhhhhhhh
    0.66
    hhh
    0.63
    ield
    0.60
    تباه
    0.60
    waukee
    0.59
    энне
    0.59
    Activations Density 0.164%

    No Known Activations