© 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. 53-GEMMASCOPE-2-RES-65K
    7. 8783
    Prev
    Next
    INDEX
    Explanations

    bathing and showering

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

    warm bath or shower

    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
    transcript
    0.40
    bracket
    0.40
    堇
    0.39
    耋
    0.39
    राल
    0.38
    偏移
    0.38
    नपुर
    0.38
    蹺
    0.37
    밈
    0.37
    চৈত
    0.36
    POSITIVE LOGITS
     bath
    3.75
     baths
    3.50
     bathing
    3.31
     bathe
    3.31
     Bath
    3.20
    bath
    3.11
     BATH
    3.09
    Bath
    3.05
    浴
    2.98
     Baths
    2.95
    Activations Density 0.103%

    No Known Activations