© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 109450
    Prev
    Next
    INDEX
    Explanations

    describingstatesorongoingactions

    np_acts-logits-general · gemini-2.5-flash-lite

    categorize text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    老人
    0.47
    热
    0.47
    ه
    0.45
    对象的
    0.44
    炀
    0.44
    楸
    0.44
    ाना
    0.43
     Yarn
    0.43
    шты
    0.42
    熙
    0.42
    POSITIVE LOGITS
     solide
    0.62
     superficie
    0.59
     Dateien
    0.57
     permukaan
    0.55
     maximale
    0.54
     erlaub
    0.54
     bruises
    0.54
    riminating
    0.54
     sporad
    0.53
     schermo
    0.53
    Activations Density 0.001%

    No Known Activations