© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1772
    Prev
    Next
    INDEX
    Explanations

    `require` or `from` followed by path imports

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

    This neuron strongly activates on string‐literal tokens that are part of code import paths or HTML link URLs.

    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
    ("
    0.64
    SOCKET
    0.61
    вёр
    0.59
    Furn
    0.56
    齙
    0.55
    No
    0.55
    ({
    0.54
    My
    0.53
    NotBlank
    0.53
    Panel
    0.53
    POSITIVE LOGITS
     './
    1.48
     '../
    1.48
     "../
    1.41
     "./
    1.34
     '../../
    1.32
     "../../
    1.27
     ../
    1.17
     ./
    1.09
     '../../../
    1.05
    ('../
    1.04
    Activations Density 0.004%

    No Known Activations