© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 6141
    Prev
    Next
    INDEX
    Explanations

    medical and bodily functions

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

    The neuron fires on content words that are verbs in their various inflected forms (e.g. –s, –ed, –ing endings).

    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
     reaffirm
    0.89
    ើង
    0.80
     चौधरी
    0.80
    ع
    0.77
     والم
    0.76
    ف
    0.75
     ImageData
    0.75
    翎
    0.73
    lessis
    0.73
     ၂
    0.72
    POSITIVE LOGITS
    ################
    0.81
    <table>
    0.73
    TER
    0.71
    SEVERE
    0.70
    <h2>
    0.69
    Vad
    0.69
    DEVELOP
    0.68
    venes
    0.67
    TEN
    0.67
    }}{
    0.67
    Activations Density 0.002%

    No Known Activations