© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 192287
    Prev
    Next
    INDEX
    Explanations

    cold, chilled, ice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     heater
    0.49
     tea
    0.44
     heaters
    0.44
    咖啡
    0.41
     heat
    0.41
     coffee
    0.41
     heather
    0.41
    radiol
    0.41
    缬
    0.40
     hydrothermal
    0.40
    POSITIVE LOGITS
     cold
    1.66
    冷
    1.63
    cold
    1.55
     chilled
    1.55
    Cold
    1.45
     Cold
    1.43
     холод
    1.38
     colder
    1.30
     dingin
    1.29
     coldest
    1.28
    Activations Density 0.027%

    No Known Activations