© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 27350
    Prev
    Next
    INDEX
    Explanations

    Type 1 Diabetes, AMD

    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_65k_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
    抗
    0.50
    倉庫
    0.45
    renamiento
    0.44
    知
    0.42
    Hire
    0.41
    待
    0.41
    重
    0.41
    ire
    0.40
    陽
    0.40
    在高
    0.40
    POSITIVE LOGITS
     anthropogenic
    0.52
    anın
    0.49
     exclusive
    0.49
     stoichi
    0.46
    ສາມາດ
    0.46
    otoxin
    0.46
     astrophys
    0.45
     WJ
    0.45
     लेनदेन
    0.44
     Secondary
    0.44
    Activations Density 0.002%

    No Known Activations