© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 52683
    Prev
    Next
    INDEX
    Explanations

    Lists, technical terms, and 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_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
     mannit
    0.48
     Ừ
    0.47
    ้วน
    0.46
    FirstFit
    0.45
     Alla
    0.44
     डिजिट
    0.44
     mette
    0.44
     Digit
    0.44
     ["
    0.43
     मंथ
    0.43
    POSITIVE LOGITS
    
    0.45
    ū
    0.45
    は
    0.45
    ケ
    0.45
     subordination
    0.44
    obacterial
    0.44
    šč
    0.43
     economic
    0.43
    )。
    0.43
     civilians
    0.43
    Activations Density 0.001%

    No Known Activations