© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5727
    Prev
    Next
    INDEX
    Explanations

    4

    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_24_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
     மற்றும்
    0.95
    )/
    0.70
     וא
    0.70
     (:
    0.67
    s
    0.67
    ཾ
    0.67
     ৪
    0.66
     denoted
    0.66
     (${
    0.66
     για
    0.64
    POSITIVE LOGITS
    這些
    0.77
    这些
    0.72
    immediate
    0.72
    ل
    0.71
    ণ্ডিত
    0.69
    us
    0.68
    adequate
    0.68
    л
    0.67
    RIGHT
    0.67
    joyed
    0.67
    Activations Density 0.003%

    No Known Activations