© 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. 40-GEMMASCOPE-2-RES-262K
    7. 166704
    Prev
    Next
    INDEX
    Explanations

    inhomogeneous and disparate concepts

    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_40_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
     없
    0.43
     těchto
    0.41
     парла
    0.41
     arka
    0.41
     परिवार
    0.41
     സര്‍
    0.40
     ন্যায্য
    0.40
     художника
    0.40
    ありません
    0.39
     ہوتا
    0.39
    POSITIVE LOGITS
     inhomogeneous
    0.41
     Title
    0.40
    蔵
    0.39
     இறை
    0.38
     mir
    0.38
    辞
    0.38
     miraculous
    0.36
     Stich
    0.36
     passages
    0.36
     abuse
    0.36
    Activations Density 0.005%

    No Known Activations