© 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. 162740
    Prev
    Next
    INDEX
    Explanations

    Australia

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

    Australia

    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
    तेरे
    0.46
    гід
    0.45
    Plastic
    0.45
    Cement
    0.43
     favourable
    0.43
     زمانی
    0.42
     favourably
    0.42
     ۾
    0.42
    Behaviour
    0.41
    Behaviours
    0.41
    POSITIVE LOGITS
     Australian
    1.27
     Australia
    1.26
     Australien
    1.22
     austral
    1.20
    澳大利亚
    1.13
     Australians
    1.11
     Aussie
    1.11
    Australia
    1.10
     Australie
    1.10
     australia
    1.09
    Activations Density 0.140%

    No Known Activations