© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7831
    Prev
    Next
    INDEX
    Explanations

    finding location on map

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

    The neuron activates on mentions of physical retail locations or store names (i.e. where to find things in shops or listings of specific commercial outlets).

    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
     nahin
    0.90
     Кстати
    0.75
     WITH
    0.74
     muß
    0.74
     ;-)
    0.73
     завое
    0.73
     vraie
    0.69
    👿
    0.68
     ..............
    0.68
     AFTER
    0.67
    POSITIVE LOGITS
     entirety
    0.94
     recieved
    0.81
    ंमध्ये
    0.79
     preexisting
    0.79
     있으며
    0.77
     మరియు
    0.77
    以及
    0.74
    existent
    0.73
     aswell
    0.72
     aesthetically
    0.71
    Activations Density 0.034%

    No Known Activations