© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9511
    Prev
    Next
    INDEX
    Explanations

    New Zealand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-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
    Not in Any Lists

    No Comments

    Negative Logits
     Maryland
    0.69
     Pennsylvania
    0.66
     gy
    0.63
     reicht
    0.63
     bolog
    0.61
     sv
    0.61
     reichen
    0.61
     ########
    0.60
     luster
    0.59
     Harrisburg
    0.59
    POSITIVE LOGITS
     NZ
    2.23
    NZ
    2.13
     Auckland
    2.08
     Otago
    1.98
     Māori
    1.96
     Maori
    1.94
     Christchurch
    1.93
     Dunedin
    1.87
     Kiwi
    1.86
     न्यूजीलैंड
    1.70
    Activations Density 0.344%

    No Known Activations