© 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. 8692
    Prev
    Next
    INDEX
    Explanations

    routing and route handlers

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

    The neuron strongly activates on mentions of “Route” or routing attributes (e.g. Route, routing, AttributeRouting) in code or documentation.

    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
     /
    0.66
     "/
    0.65
    ","/
    0.64
     useEffect
    0.62
     Telangana
    0.62
     Sánchez
    0.61
     '/
    0.60
     axios
    0.59
     López
    0.59
    ☮
    0.57
    POSITIVE LOGITS
    trailing
    0.61
    Trailing
    0.59
     segmentos
    0.58
    トレー
    0.56
    常量
    0.54
    Constraints
    0.54
    alphas
    0.52
     සම්බන්ධ
    0.52
    grads
    0.51
     कार्यकर्त्या
    0.50
    Activations Density 0.006%

    No Known Activations