© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 192167
    Prev
    Next
    INDEX
    Explanations

    Arctic phenomena and geography

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

    Arctic and polar wildlife

    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_31_width_262k_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
    enciones
    0.44
    ferm
    0.41
    荥
    0.40
    mene
    0.40
    原始内容
    0.39
    謦
    0.39
    蒂
    0.39
    淅
    0.39
    耑
    0.39
    簽證
    0.39
    POSITIVE LOGITS
     Arctic
    0.96
    Arctic
    0.89
     arctic
    0.87
     Sval
    0.73
    arctic
    0.67
     Inuit
    0.66
     ice
    0.66
     tundra
    0.63
     Greenland
    0.59
     Ice
    0.59
    Activations Density 0.042%

    No Known Activations