© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 1513
    Prev
    Next
    INDEX
    Explanations

    The neuron mainly detects references to “.js” JavaScript file names or extensions in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    line breaks or newlines in code and technical documentation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of JavaScript files, especially .js filenames and paths in technical or build/output text.

    oai_token-act-pair · gpt-5Triggered 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
     '}';
    0.71
     يبقى
    0.66
     nadzie
    0.63
     }}
    0.62
     ")");
    0.62
     JsonResult
    0.62
     Khim
    0.61
     Untitled
    0.60
    }}}
    0.59
     $-\
    0.59
    POSITIVE LOGITS
    const
    1.11
    require
    0.98
    import
    0.92
    /**
    0.92
    var
    0.88
    //#
    0.86
    /***
    0.81
     require
    0.79
     const
    0.76
    let
    0.73
    Activations Density 0.004%

    No Known Activations