© 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
    3. 53-GEMMASCOPE-2-RES-65K
    4. 1282
    Prev
    Next
    INDEX
    Explanations

    heat and temperature

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

    heat or generating heat

    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
     remboursement
    0.38
     እድ
    0.36
    ষ্ট্র
    0.36
    ნის
    0.35
    寰
    0.35
    鷸
    0.35
     Oldborough
    0.35
    actionMode
    0.35
     विराम
    0.34
     souver
    0.34
    POSITIVE LOGITS
    热
    3.73
     hot
    3.67
    熱
    3.56
     hotter
    3.41
     heat
    3.39
     sıcak
    3.33
     热
    3.31
     गर्म
    3.20
     warm
    3.16
     HOT
    3.16
    Activations Density 0.514%

    No Known Activations