© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 20641
    Prev
    Next
    INDEX
    Explanations

    Chinese punctuation and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    ،
    0.78
     -.
    0.61
     ،
    0.59
     paddock
    0.57
     blight
    0.56
     filamentous
    0.56
     fuselage
    0.56
     ductile
    0.55
     ,
    0.55
    ных
    0.55
    POSITIVE LOGITS
    其
    0.79
    而且
    0.77
    它
    0.71
    他的
    0.70
    你
    0.69
    使用
    0.67
    我们
    0.66
    我
    0.65
    他
    0.65
    所有
    0.64
    Activations Density 0.008%

    No Known Activations