© 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. 15487
    Prev
    Next
    INDEX
    Explanations

    domestic cases

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

    The neuron strongly fires on the “-ing” suffix in words, effectively detecting gerund/participle forms.

    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
    kend
    0.96
     möglicherweise
    0.79
    sen
    0.78
     comerciais
    0.78
    Máy
    0.77
     signifikan
    0.77
    sensing
    0.76
    Ü
    0.76
    sel
    0.75
    IO
    0.75
    POSITIVE LOGITS
     н
    0.86
    ження
    0.77
    ゛
    0.75
     bracket
    0.74
     صد
    0.73
     ち
    0.73
     않고
    0.72
     ৰ
    0.72
     ਭ
    0.70
     қ
    0.69
    Activations Density 0.000%

    No Known Activations