© 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. 114051
    Prev
    Next
    INDEX
    Explanations

    htmltagclosing

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

    closing HTML/XML tags, particularly `</span>` and `</font>`.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @bfgcn7frf5

    The neuron activates on tokens that are standalone numbers or numeric values (including integers, decimals, and percentages).

    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
     to
    -1.56
    칭
    -1.55
     However
    -1.51
     stano
    -1.44
    でも
    -1.44
     tarifa
    -1.43
    穷
    -1.41
     mencegah
    -1.41
    Berikut
    -1.39
    Gön
    -1.39
    POSITIVE LOGITS
     nunmehr
    1.80
     a
    1.80
    
    1.79
     indeb
    1.72
    still
    1.72
    ⅰ
    1.70
    usually
    1.64
    phile
    1.63
    
    1.60
    addCriterion
    1.59
    Activations Density 0.009%

    No Known Activations