© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38494
    Prev
    Next
    INDEX
    Explanations

    intersection points

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

    The neuron activates on occurrences of the word stem “intersect” (e.g. “intersection,” “intersecting”) in the text.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ꔹ
    -2.77
    琑
    -2.73
    your
    -2.72
    with
    -2.58
     یا
    -2.53
    like
    -2.47
    筇
    -2.44
    We
    -2.44
    屺
    -2.44
    大的
    -2.41
    POSITIVE LOGITS
    珦
    3.22
    ஂ
    3.00
    咵
    2.98
    
    2.77
    潆
    2.77
    驀
    2.77
    ୌ
    2.69
     continúas
    2.67
    歃
    2.59
    鈇
    2.59
    Activations Density 0.004%

    No Known Activations