© 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. 136208
    Prev
    Next
    INDEX
    Explanations

    SPA Model, Limited Edition

    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
     সহিংস
    0.47
    affold
    0.45
     breastfeeding
    0.44
     investigating
    0.43
     overseeing
    0.43
     investigate
    0.42
     tox
    0.41
    橋
    0.41
     suspicious
    0.40
     raided
    0.40
    POSITIVE LOGITS
     верхней
    0.54
     सगळे
    0.46
     ทาง
    0.46
    ت
    0.46
     дело
    0.45
     மாணவர்கள்
    0.44
    Words
    0.44
    Maximum
    0.44
    т
    0.43
    ทาง
    0.42
    Activations Density 0.003%

    No Known Activations