© 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. 1947
    Prev
    Next
    INDEX
    Explanations

    dynamic motion or intense states

    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
    ли
    1.88
    ні
    1.80
    ye
    1.73
    heids
    1.63
    ors
    1.58
    я
    1.56
    í
    1.56
    ки
    1.52
    ario
    1.50
    ності
    1.50
    POSITIVE LOGITS
    ل
    1.81
    الم
    1.73
    あえず
    1.60
    الب
    1.57
     macaw
    1.48
    Khal
    1.47
    不支持
    1.46
    녘
    1.46
    Бе
    1.44
    П
    1.44
    Activations Density 0.130%

    No Known Activations