© 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. 12-GEMMASCOPE-2-RES-262K
    7. 31897
    Prev
    Next
    INDEX
    Explanations

    beautiful artistic expression

    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
    いない
    1.66
    有哪些
    1.57
     えっ
    1.55
    하는
    1.54
    (\
    1.53
    (
    1.51
    ‌است
    1.47
    {
    1.45
     acquitted
    1.42
    おり
    1.41
    POSITIVE LOGITS
    er
    1.89
    ş
    1.83
    a
    1.63
    ü
    1.62
    ль
    1.55
    گ
    1.55
    í
    1.52
    enums
    1.51
    л
    1.51
    ا
    1.50
    Activations Density 0.000%

    No Known Activations