© 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. 11938
    Prev
    Next
    INDEX
    Explanations

    French place names and addresses

    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
     squared
    0.59
     Square
    0.57
    棱
    0.57
     جنوب
    0.56
     ದ
    0.55
     "*
    0.54
     sq
    0.54
     square
    0.53
     Sq
    0.52
     nk
    0.51
    POSITIVE LOGITS
    «
    0.63
    తూ
    0.58
     prevención
    0.58
    Chapters
    0.57
    েশের
    0.57
     capítulos
    0.57
     métodos
    0.55
     estética
    0.55
     गठ
    0.55
    টাতে
    0.55
    Activations Density 0.010%

    No Known Activations