© 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. 1790
    Prev
    Next
    INDEX
    Explanations

    variable declaration syntax

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

    The neuron fires on CamelCase or PascalCase identifier tokens (e.g. class, field, parameter, or function names) in code and docs.

    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
    +="
    0.42
    წერ
    0.38
    ائیں۔
    0.37
    库
    0.36
    ັບ
    0.34
    ئیں۔
    0.34
    ならでは
    0.34
    aların
    0.33
    谲
    0.33
    یں۔
    0.33
    POSITIVE LOGITS
    ;
    0.63
     ;
    0.54
    ؛
    0.51
     ؛
    0.51
     –
    0.50
     ¬
    0.49
     ()
    0.49
       
    0.48
      
    0.47
     EDT
    0.47
    Activations Density 0.001%

    No Known Activations