© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8350
    Prev
    Next
    INDEX
    Explanations

    providing support

    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
     pénétr
    0.49
    ineas
    0.47
    邂
    0.47
    䀘
    0.47
     многим
    0.46
     वैशिष्ट
    0.46
    工夫
    0.45
    柔らか
    0.45
    
    0.45
     ingenious
    0.45
    POSITIVE LOGITS
     support
    3.67
     Support
    3.30
    Support
    3.27
    支持
    3.25
    support
    3.23
     SUPPORT
    3.13
     지원
    3.05
     поддержки
    3.03
     поддержку
    3.02
     supporting
    2.97
    Activations Density 0.554%

    No Known Activations