© 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-262K
    7. 34754
    Prev
    Next
    INDEX
    Explanations

    paradigms, communication, categories

    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
    ۇل
    0.46
     gagner
    0.43
     ደቂ
    0.42
     gewährleisten
    0.41
     dê
    0.39
     জাহান
    0.39
    Wallace
    0.39
    >',
    0.39
     chiefly
    0.38
     ngũ
    0.38
    POSITIVE LOGITS
    也要
    0.50
     conjure
    0.46
     말고
    0.45
    ໂຕ
    0.44
     PSR
    0.44
     remastered
    0.44
     बीएसटीसी
    0.43
     PVC
    0.42
    лимпий
    0.42
    절
    0.41
    Activations Density 0.000%

    No Known Activations