© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5404
    Prev
    Next
    INDEX
    Explanations

    branches intertwined

    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
    用力
    0.63
    能量
    0.63
    ()?
    0.57
     사람이
    0.56
    grasp
    0.56
    uric
    0.55
     admirer
    0.55
    哪
    0.55
    部位
    0.55
     frightened
    0.54
    POSITIVE LOGITS
     backdrop
    0.68
     blurring
    0.66
     Stretching
    0.64
     Like
    0.61
     والصلاه
    0.61
     ذہن
    0.61
     Against
    0.59
     overhead
    0.57
     Overhead
    0.56
     Lazy
    0.56
    Activations Density 0.253%

    No Known Activations