© 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. 2502
    Prev
    Next
    INDEX
    Explanations

    python and java imports

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find mentions of the word “Bollywood.”

    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
     συμμε
    0.82
    </h3>
    0.77
    thisComponent
    0.71
    fqsen
    0.69
    έ
    0.68
     구성
    0.67
    ь
    0.67
    托
    0.67
    SOI
    0.66
     غور
    0.66
    POSITIVE LOGITS
     آمریکا
    0.77
    况
    0.76
    ilizce
    0.74
    रों
    0.73
    યા
    0.72
    czne
    0.72
    பாடு
    0.71
     consulate
    0.71
     saints
    0.71
     perjanjian
    0.71
    Activations Density 0.000%

    No Known Activations