© 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. 24-GEMMASCOPE-2-RES-16K
    7. 1994
    Prev
    Next
    INDEX
    Explanations

    places names and locations

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

    The neuron detects mentions of place names and other proper‐noun geographic landmarks.

    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_24_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
     tầng
    0.59
    ገኛ
    0.54
    በባ
    0.54
     গেরিলা
    0.52
    abhave
    0.52
    iend
    0.50
     স্টেট
    0.50
    楇
    0.50
    Criterion
    0.50
    elerde
    0.49
    POSITIVE LOGITS
     Nasional
    0.61
     Londres
    0.59
     montagne
    0.58
     anglais
    0.58
     David
    0.56
     San
    0.55
    -
    0.55
     lainnya
    0.54
     America
    0.54
     Antonio
    0.54
    Activations Density 0.074%

    No Known Activations