© 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. 11425
    Prev
    Next
    INDEX
    Explanations

    closing punctuation or code blocks

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

    This neuron strongly activates on JavaScript module filenames (tokens ending in “.js”).

    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
    getattr
    0.80
    #
    0.79
    )#
    0.77
    #%%
    0.75
    ExposureTime
    0.74
    assertRaises
    0.71
    parametrize
    0.68
    )%
    0.68
    %
    0.66
    :#
    0.65
    POSITIVE LOGITS
    ”;
    0.74
    »;
    0.71
     .”
    0.70
     「
    0.68
     -"
    0.67
     ”
    0.66
     \""
    0.66
     UIS
    0.65
     setUser
    0.64
     «
    0.63
    Activations Density 0.000%

    No Known Activations