© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 13318
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly fires on adverbs and prepositions (e.g. “even,” “by,” “through,” “most,” “all”) that signal manner, extent, or means.

    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
     трубо
    0.83
    ในปี
    0.73
    FAs
    0.72
     προϊ
    0.71
    ų
    0.70
    ในการ
    0.70
     ткани
    0.69
     theologians
    0.69
    愷
    0.68
    iteit
    0.68
    POSITIVE LOGITS
    eed
    0.90
     maximise
    0.84
    ei
    0.83
     maximize
    0.81
    eek
    0.80
    ب
    0.79
     asterisk
    0.79
     نهایت
    0.78
     browse
    0.76
    enary
    0.76
    Activations Density 0.000%

    No Known Activations