© 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. 1714
    Prev
    Next
    INDEX
    Explanations

    arrival and visiting

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

    The neuron activates on numeric tokens (numbers, statistics, or digit‐containing references).

    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
    ння
    0.90
    ς
    0.88
    т
    0.78
    Categorie
    0.75
     কী
    0.75
    বাজ
    0.75
     hvad
    0.74
    𝟎
    0.74
    ום
    0.73
    Occupation
    0.72
    POSITIVE LOGITS
    visit
    0.88
     Visits
    0.88
     visitas
    0.87
     visite
    0.87
     Hospitals
    0.87
    cafe
    0.83
    お店
    0.82
     Factories
    0.82
    shops
    0.82
     Helps
    0.81
    Activations Density 0.040%

    No Known Activations