© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11308
    Prev
    Next
    INDEX
    Explanations

    arctic and antarctic regions

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

    arctic, Antarctic, and Alaskan ice and tundra

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

    Arctic regions

    np_max-act-logits · claude-4-5-sonnet
    Triggered by @skarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    okkh
    0.46
    蚕
    0.45
    苎
    0.45
    zzet
    0.44
     Guadalajara
    0.43
    eban
    0.43
     acá
    0.42
    翳
    0.42
     डायबिटीज
    0.41
     যশোর
    0.41
    POSITIVE LOGITS
     Arctic
    1.53
     arctic
    1.45
    Arctic
    1.45
     Alaska
    1.41
     tundra
    1.40
    Alaska
    1.34
     Alaskan
    1.34
     Antarctic
    1.24
     Antarctica
    1.23
     Greenland
    1.23
    Activations Density 0.318%

    No Known Activations