© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9626
    Prev
    Next
    INDEX
    Explanations

    outdoor or external contexts

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

    The neuron strongly activates on words referring to being outside or outdoors.

    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_31_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
    内部
    0.64
    內部
    0.60
     internal
    0.60
     Internal
    0.60
    Internal
    0.59
     داخلی
    0.57
    内
    0.56
     Interior
    0.56
    내
    0.56
    كون
    0.54
    POSITIVE LOGITS
     Outside
    0.68
    甥
    0.66
     बराम
    0.65
    在外
    0.64
    outside
    0.64
     बाहरी
    0.63
     terrestre
    0.62
     exteriores
    0.61
    곽
    0.60
     facing
    0.59
    Activations Density 0.123%

    No Known Activations