© 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. 10181
    Prev
    Next
    INDEX
    Explanations

    country names

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

    The neuron fires on proper nouns naming geographic locations (towns and cities).

    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
    водит
    0.58
    மானது
    0.57
     `>=
    0.57
     burdensome
    0.57
    মাণের
    0.55
    ডাক্ট
    0.55
     конкурен
    0.55
     ingrained
    0.54
    ண்டும்
    0.54
    ானது
    0.54
    POSITIVE LOGITS
    ،
    0.71
     ،
    0.70
    ၊
    0.66
    ，
    0.66
    ‚
    0.64
     ,
    0.60
     cinci
    0.57
    ¸
    0.57
    as
    0.55
     fünf
    0.55
    Activations Density 0.010%

    No Known Activations