© 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-262K
    7. 192383
    Prev
    Next
    INDEX
    Explanations

    Antarctic geography and penguins

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

    penguins and their habitats

    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
    Negative Logits
    Mexico
    0.59
     तेलंगाना
    0.56
     Yucatan
    0.52
    Mexican
    0.50
     Mexico
    0.49
    嫘
    0.49
     निजामाच्या
    0.49
    Chhattisgarh
    0.49
    傣
    0.47
     Mexiko
    0.47
    POSITIVE LOGITS
     Antarctic
    1.34
     Antarctica
    1.13
    南極
    1.07
     penguin
    0.94
     penguins
    0.92
     Chilean
    0.79
     Penguins
    0.76
     Patagonia
    0.76
     Tasmania
    0.75
     austral
    0.71
    Activations Density 0.113%

    No Known Activations