© 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. 12100
    Prev
    Next
    INDEX
    Explanations

    places in England and India

    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
     Lhasa
    0.64
     Carpath
    0.63
     Tibetan
    0.63
     Tibet
    0.62
    盪
    0.62
     उत्तराखण्ड
    0.61
     Carpathians
    0.60
     Danube
    0.59
     Columbia
    0.59
    漕
    0.59
    POSITIVE LOGITS
    Alabama
    2.25
     Alabama
    2.23
    Birmingham
    2.05
     Birmingham
    2.00
     Huntsville
    1.49
     Auburn
    1.24
     Warwickshire
    1.13
     Bahrain
    1.10
    irmingham
    1.08
    福岡
    1.04
    Activations Density 0.314%

    No Known Activations