© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11279
    Prev
    Next
    INDEX
    Explanations

    character, characterization, generation, traits

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

    character

    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_40_width_16k_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
    야
    0.52
    功能的
    0.50
    ب
    0.50
    बस
    0.49
    สำเร็จ
    0.49
    機能
    0.49
    മ
    0.49
    पा
    0.48
     thousand
    0.48
    ग
    0.47
    POSITIVE LOGITS
     Charakter
    0.80
    istically
    0.73
     Character
    0.72
    Character
    0.71
    itics
    0.68
     charakter
    0.65
    istical
    0.58
     характер
    0.57
    ization
    0.55
    character
    0.55
    Activations Density 0.097%

    No Known Activations