© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 23506
    Prev
    Next
    INDEX
    Explanations

    polar regions and associated geography

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tree
    -0.87
    ᓕ
    -0.72
     TREES
    -0.68
     турни
    -0.68
     trees
    -0.68
    鳟
    -0.68
    miary
    -0.67
    ต้น
    -0.66
     groundwater
    -0.66
     Ammon
    -0.66
    POSITIVE LOGITS
     Antarctic
    2.16
     polar
    2.06
     Polar
    2.03
    Polar
    1.97
     Antarctica
    1.95
     Arctic
    1.92
    polar
    1.84
    Arctic
    1.66
     arctic
    1.60
     Greenland
    1.55
    Activations Density 0.062%

    No Known Activations