© 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. 12163
    Prev
    Next
    INDEX
    Explanations

    capital city of

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

    The neuron fires on the main noun in multi‐word noun phrases—i.e. the head noun of compound or technical terms.

    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
    P
    0.70
    U
    0.68
    i
    0.66
     devrait
    0.63
    ap
    0.61
    H
    0.61
    ニメ
    0.59
    亼
    0.59
    ス
    0.59
    zelf
    0.58
    POSITIVE LOGITS
                        
    0.71
     которой
    0.71
    ়া
    0.71
     of
    0.69
     Донец
    0.68
     (?)
    0.67
     краси
    0.66
    0.66
     которого
    0.65
     ਅਤੇ
    0.65
    Activations Density 0.656%

    No Known Activations