© 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. 1207
    Prev
    Next
    INDEX
    Explanations

    place names

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

    The neuron strongly activates on proper nouns that are place names or geographic locations (e.g. cities, towns, regions).

    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
    UIntValue
    0.91
    ፈላጊ
    0.84
     ridicule
    0.80
     пи
    0.79
     `'\\
    0.79
    DrvGPIO
    0.78
     sarcastic
    0.77
     impure
    0.77
     слабы
    0.77
     mockery
    0.77
    POSITIVE LOGITS
    .
    1.40
     selatan
    1.29
     Selatan
    1.27
     outskirts
    1.20
    ,
    1.20
     County
    1.16
     Üniversitesi
    1.15
     Utara
    1.11
    .,
    1.10
     City
    1.10
    Activations Density 3.106%

    No Known Activations