© 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. 22771
    Prev
    Next
    INDEX
    Explanations

    English names followed by other English words

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

    This neuron responds to long punctuation tokens—especially em‐dashes and map/arrow symbols—used as separators or typographic dividers.

    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
     Our
    -3.02
     Primarily
    -2.83
    どうなる
    -2.61
     verbess
    -2.52
     Currently
    -2.44
     Eindruck
    -2.39
    Although
    -2.38
     Right
    -2.34
    两年
    -2.33
    聳
    -2.31
    POSITIVE LOGITS
    鬭
    3.09
    埽
    2.94
    糴
    2.63
     canaux
    2.55
    u
    2.52
     uſed
    2.50
    硨
    2.48
    鹉
    2.44
    鼱
    2.42
    .​
    2.41
    Activations Density 0.001%

    No Known Activations