© 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. 6876
    Prev
    Next
    INDEX
    Explanations

    contextual temperature readings

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

    measuring temperature

    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
     финансо
    0.43
    金融
    0.43
     financière
    0.41
    栨
    0.40
     நிதி
    0.39
    वित्त
    0.38
    财务
    0.38
     финансовых
    0.38
    财
    0.38
     financiar
    0.38
    POSITIVE LOGITS
     temperature
    4.56
     Temperature
    4.28
    温度
    4.25
     temperatures
    4.16
    temperature
    4.16
    Temperature
    4.13
     temperatura
    4.09
     température
    3.98
     temperatur
    3.98
    溫度
    3.94
    Activations Density 0.204%

    No Known Activations