© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13538
    Prev
    Next
    INDEX
    Explanations

    paramilitary, laughter died, bunch of equations

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

    The neuron strongly activates only on the adverb “much.”

    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
     alltid
    0.76
    enl
    0.71
    uzione
    0.70
    ø
    0.70
     direkte
    0.69
     असतो
    0.68
    ละเอียด
    0.67
    at
    0.66
    ב
    0.66
    <0xB5>
    0.66
    POSITIVE LOGITS
     ምን
    0.78
     लकड़ी
    0.78
     extingu
    0.77
     инструментов
    0.76
     andolan
    0.74
    ່ງ
    0.73
     грузо
    0.73
    Гор
    0.73
     ото
    0.72
     были
    0.72
    Activations Density 0.000%

    No Known Activations