© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10243
    Prev
    Next
    INDEX
    Explanations

    verbs followed by actions

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

    The neuron primarily responds to numeric tokens—years, measurements, counts, and other number-like values.

    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_31_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
     approx
    0.88
     –
    0.83
     terdapat
    0.82
     в
    0.81
     Eesti
    0.80
     betreff
    0.79
     tych
    0.78
     č
    0.77
     incompre
    0.77
     š
    0.75
    POSITIVE LOGITS
     adimensional
    0.84
    록
    0.79
     planification
    0.79
     tweaked
    0.76
     confortable
    0.75
     unapolog
    0.75
    녀
    0.75
     underwhelming
    0.74
    드를
    0.73
    벅
    0.73
    Activations Density 0.185%

    No Known Activations