© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 5063
    Prev
    Next
    INDEX
    Explanations

    costumes and uniforms

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

    worn items and clothing

    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_53_width_65k_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
    isHorizontal
    0.38
     yì
    0.38
    idyl
    0.37
    SQLException
    0.36
    ępnie
    0.36
    洨
    0.36
     કિ
    0.35
    🖇
    0.35
    뷰
    0.35
    itori
    0.35
    POSITIVE LOGITS
     uniforms
    2.39
     костю
    2.39
     costumes
    2.19
     لباس
    2.17
     costume
    2.08
     uniform
    2.06
     attire
    2.03
     helmets
    2.03
     robes
    2.03
     পোশাক
    2.03
    Activations Density 0.234%

    No Known Activations