© 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-16K
    7. 7819
    Prev
    Next
    INDEX
    Explanations

    Temporal and causal 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_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
    症状
    0.41
     Therapy
    0.39
     बढ़ाता
    0.39
    囧
    0.39
     ဒါ
    0.39
    อม
    0.38
    یە
    0.37
     però
    0.37
     эмоциона
    0.36
    ጮ
    0.36
    POSITIVE LOGITS
    ientras
    0.55
     WHILE
    0.48
     waardoor
    0.46
     mientras
    0.46
     lorsqu
    0.46
    하여
    0.45
    使其
    0.44
    ogh
    0.44
     wodurch
    0.43
    ながら
    0.43
    Activations Density 0.250%

    No Known Activations