© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2510
    Prev
    Next
    INDEX
    Explanations

    south of Italy

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

    This neuron detects temporal and locative context markers—prepositions like “in,” “on,” “at,” and associated numeric dates or place indicators.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     інших
    1.03
     innych
    0.93
     других
    0.92
     各
    0.87
     drugih
    0.82
     dalších
    0.80
     любых
    0.80
     ailleurs
    0.77
     각
    0.75
     любые
    0.74
    POSITIVE LOGITS
     sogenannte
    0.79
     sogenannten
    0.77
     مدينة
    0.77
     southwestern
    0.71
    approximately
    0.70
     suburban
    0.68
     suburb
    0.68
     sogen
    0.67
     outskirts
    0.67
    非常に
    0.66
    Activations Density 0.519%

    No Known Activations