© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52089
    Prev
    Next
    INDEX
    Explanations

    conversion, excellent, prediction, clinical

    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
     機械
    0.46
    🏰
    0.46
     بندر
    0.45
     режисс
    0.45
    ალა
    0.45
    مین
    0.44
     канторы
    0.44
    ༣
    0.44
     স্টি
    0.43
    🍦
    0.43
    POSITIVE LOGITS
     encephalitis
    0.57
     inflammatory
    0.57
     clinically
    0.55
     infections
    0.55
     lactic
    0.54
     allergic
    0.54
     antibodies
    0.54
     inflammation
    0.53
     ulcerative
    0.53
     clinical
    0.52
    Activations Density 0.003%

    No Known Activations