© 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. 22-GEMMASCOPE-RES-131K
    7. 25129
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code

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

    The neuron fires on sequences that enumerate characters or digits in order (e.g. listing “a, b, c … w, x, y, z” or “1, 2, 3 … 8, 9”).

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     expertise
    -0.96
    ểu
    -0.93
     нужен
    -0.91
     sembler
    -0.90
    ρυ
    -0.90
    就被
    -0.88
    expertise
    -0.87
    ingeki
    -0.86
    Frem
    -0.85
     Lecce
    -0.85
    POSITIVE LOGITS
     as
    0.97
     atve
    0.94
     when
    0.84
     to
    0.81
     '@/
    0.75
    пин
    0.75
    lées
    0.74
     १
    0.73
    ⫺
    0.73
    Center
    0.73
    Activations Density 0.017%

    No Known Activations