© 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. 5782
    Prev
    Next
    INDEX
    Explanations

    package installation commands

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

    The neuron fires on technical software package or library identifiers—particularly hyphenated names with numbers (e.g. “lib-pcre3-dev,” kernel versions, bootloader names, Raspberry Pi components).

    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
    demo
    0.70
    Demo
    0.65
    proyecto
    0.64
    module
    0.61
    ../../
    0.58
    ···
    0.55
    components
    0.55
     demo
    0.55
     ಅವರನ್ನು
    0.55
    ../../../
    0.54
    POSITIVE LOGITS
     PNG
    0.73
     JPEG
    0.73
     jpeg
    0.73
     Newtonsoft
    0.72
     gson
    0.70
     Postgres
    0.70
     HttpClient
    0.70
     Javascript
    0.66
     Rendering
    0.66
     PostgreSQL
    0.66
    Activations Density 0.023%

    No Known Activations