© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2628
    Prev
    Next
    INDEX
    Explanations

    maintaining coolness

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

    temperature and cooling

    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
     গের
    0.37
     ফেব্রুয়ার
    0.36
     පේශ
    0.35
    耆
    0.35
    commit
    0.34
    獪
    0.34
    燭
    0.34
    鶯
    0.34
     Nonlinear
    0.33
    手数
    0.33
    POSITIVE LOGITS
     cool
    4.25
    Cool
    4.16
     COOL
    4.13
     Cool
    4.09
    cool
    4.06
     cooling
    4.03
     cools
    4.00
    COOL
    3.97
     cooled
    3.95
     coolness
    3.92
    Activations Density 0.294%

    No Known Activations