© 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. 110165
    Prev
    Next
    INDEX
    Explanations

    Generative Adversarial Network

    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
     Geography
    0.53
     prank
    0.47
     comedy
    0.45
     History
    0.44
     Risk
    0.44
     Banking
    0.43
     in
    0.43
    ൗ
    0.43
     Pottery
    0.43
    嗨
    0.43
    POSITIVE LOGITS
     общество
    0.44
    実際の
    0.43
     اصلی
    0.42
     организм
    0.41
     выде
    0.41
    嬬
    0.40
    ığını
    0.40
    cyclopent
    0.40
    ulièrement
    0.39
    দিগকে
    0.39
    Activations Density 0.006%

    No Known Activations