© 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. 24-GEMMASCOPE-2-RES-16K
    7. 12164
    Prev
    Next
    INDEX
    Explanations

    followed by punctuation or separators

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

    The neuron fires on mentions of specific places or venue names (e.g. guesthouse names, map spots, geographic locations).

    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
    <eos>
    1.29
    /'
    0.69
    টেও
    0.67
    :'
    0.66
    ;'
    0.64
    :'.
    0.64
    ''.
    0.64
    \/
    0.63
    ៕
    0.61
    =.
    0.61
    POSITIVE LOGITS
     দার্শন
    0.84
     多く
    0.80
     這個
    0.76
     നിരവധി
    0.75
     我們
    0.73
     それぞれ
    0.72
     Unlike
    0.72
     Mỗi
    0.72
     YouTuber
    0.71
     Это
    0.71
    Activations Density 0.000%

    No Known Activations