© 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. 1496
    Prev
    Next
    INDEX
    Explanations

    three sentence

    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
     ตั้ง
    0.70
     已
    0.62
     AcOH
    0.62
     ถ้า
    0.61
     lentils
    0.60
     교
    0.59
     Ι
    0.59
     例如
    0.59
     Bioinformatics
    0.58
     cucumbers
    0.58
    POSITIVE LOGITS
    year
    0.60
     दिवसीय
    0.60
    minute
    0.58
    questions
    0.54
     वर्षीय
    0.54
    authentic
    0.52
    短
    0.52
    weekly
    0.52
    kilometer
    0.52
     सदस्यीय
    0.51
    Activations Density 0.170%

    No Known Activations