© 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. 12-GEMMASCOPE-2-RES-262K
    7. 10058
    Prev
    Next
    INDEX
    Explanations

    May followed by verb

    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_12_width_262k_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
    д
    1.91
     maximizes
    1.90
     minimizes
    1.87
     optimizes
    1.78
    З
    1.74
     parfait
    1.71
     verifies
    1.70
     subscrib
    1.70
     simulates
    1.67
     catalyzes
    1.67
    POSITIVE LOGITS
     mắn
    2.34
    ్
    2.00
    re
    1.91
    te
    1.91
    lene
    1.91
    ารย์
    1.88
    αν
    1.87
    l
    1.87
    ۰۰
    1.86
    lık
    1.84
    Activations Density 0.114%

    No Known Activations