© 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. 11911
    Prev
    Next
    INDEX
    Explanations

    `=`, `==`, `||`, `:=` operators

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

    The neuron fires on numeric literal tokens (integers or floating-point constants) in code.

    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
    )
    1.33
    ")
    1.28
    ）
    1.26
     )
    1.23
    ')
    1.18
     _)
    1.18
     "")
    1.17
    ’)
    1.16
    ,)
    1.13
     '')
    1.11
    POSITIVE LOGITS
    ;
    3.11
    !;
    2.81
    *;
    2.78
     [];
    2.75
    ?;
    2.67
     "";
    2.66
    ；
    2.66
    $;
    2.64
    ();
    2.61
     {};
    2.61
    Activations Density 0.001%

    No Known Activations