© 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. 8900
    Prev
    Next
    INDEX
    Explanations

    occasional

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

    The neuron strongly responds to mentions of roads, lanes, traffic, and related cycling route features.

    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
    currently
    0.77
     wrongful
    0.77
    বর্তমান
    0.75
    なのです
    0.75
    このように
    0.75
     vínculo
    0.74
    今の
    0.73
    🙅
    0.73
    そのため
    0.71
     atualmente
    0.71
    POSITIVE LOGITS
     encountered
    1.16
     occasional
    1.02
     interspersed
    1.02
     Occasionally
    1.00
     jsem
    0.99
     furent
    0.98
     jsme
    0.98
     occasionally
    0.97
     outcrops
    0.95
    几次
    0.94
    Activations Density 0.438%

    No Known Activations