© 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. 2973
    Prev
    Next
    INDEX
    Explanations

    cities and countries

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

    The neuron predominantly fires on named geographic locations (e.g., city or country names).

    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
    ,
    0.42
    ↵
    0.41
    ો
    0.40
    Notable
    0.39
    м
    0.39
     Fakat
    0.38
     (
    0.37
    ات
    0.37
    ς
    0.37
    ्स
    0.37
    POSITIVE LOGITS
     logarithm
    0.38
     cương
    0.37
    floxacin
    0.37
    tanggal
    0.37
     chá
    0.36
    ündung
    0.36
    тический
    0.35
    গারে
    0.35
    arrayList
    0.34
     gering
    0.34
    Activations Density 0.002%

    No Known Activations