© 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. 45387
    Prev
    Next
    INDEX
    Explanations

    diffusion tensor and coefficients

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

    The neuron strongly activates on the technical term “diffusion.”

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    as
    -2.63
    ي
    -2.42
     или
    -2.41
     sociala
    -2.41
    涠
    -2.36
    玏
    -2.31
    os
    -2.30
     каже
    -2.28
     was
    -2.27
     ваше
    -2.23
    POSITIVE LOGITS
    .
    3.19
    ↵
    2.94
    <bos>
    2.77
     "
    2.48
    ︲
    2.22
    灩
    2.14
    ㉕
    2.06
     genç
    2.06
     แต่
    2.00
     serán
    1.98
    Activations Density 0.003%

    No Known Activations