© 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. 24-GEMMASCOPE-2-RES-16K
    7. 672
    Prev
    Next
    INDEX
    Explanations

    SQL data types (VARCHAR, TEXT, INTEGER)

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

    The neuron fires on programming‐style data type names (e.g. string, integer, char, varchar, boolean).

    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_24_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
    他們的
    0.47
    是他
    0.46
    夏の
    0.45
    Circles
    0.45
    नाची
    0.45
    我的
    0.44
    沱
    0.43
    比起
    0.43
    散热
    0.43
    jours
    0.42
    POSITIVE LOGITS
     которые
    0.53
     which
    0.52
     varchar
    0.51
     required
    0.48
     ซึ่ง
    0.47
     REQUIRED
    0.47
     которое
    0.46
     ที่
    0.46
     Required
    0.46
    0.45
    Activations Density 0.000%

    No Known Activations