© 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-65K
    7. 54787
    Prev
    Next
    INDEX
    Explanations

    uniform distribution

    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
    Violation
    0.42
    前期
    0.41
    Religious
    0.40
     مذہبی
    0.40
    และการ
    0.39
     ایران
    0.38
    栻
    0.38
     واقعہ
    0.38
    🇪
    0.38
     tahun
    0.38
    POSITIVE LOGITS
     valleys
    0.46
     glands
    0.46
     scallops
    0.42
     flanges
    0.42
     sequentially
    0.42
     boldly
    0.42
     dozens
    0.41
     ditches
    0.41
     batches
    0.41
     carve
    0.41
    Activations Density 0.003%

    No Known Activations