© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5226
    Prev
    Next
    INDEX
    Explanations

    point

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

    The neuron strongly responds to occurrences of the word “point,” especially in the common construction “point of ….”

    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
    গুপ্ত
    0.68
     gespe
    0.64
    敍
    0.62
     CHARSET
    0.61
     Arten
    0.61
     incluindo
    0.61
     Citizenship
    0.61
     bölümde
    0.61
     HDL
    0.60
    liny
    0.60
    POSITIVE LOGITS
    点的
    1.60
    点
    1.45
     point
    1.43
     POINT
    1.43
    POINT
    1.42
    點
    1.42
    Point
    1.41
     Point
    1.40
    point
    1.39
     точку
    1.30
    Activations Density 0.174%

    No Known Activations