© 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. 34-GEMMASCOPE-RES-131K
    7. 106127
    Prev
    Next
    INDEX
    Explanations

    non-english words and code snippets

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

    This neuron activates on numeric literals—i.e. tokens composed of digits.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    克兰
    -0.92
     costura
    -0.90
     minden
    -0.85
    殆
    -0.85
     Diese
    -0.82
    новая
    -0.82
     duomen
    -0.82
    出来た
    -0.82
    bkz
    -0.80
    xda
    -0.79
    POSITIVE LOGITS
     möglicherweise
    0.85
    ノー
    0.78
    ază
    0.77
    Ꮐ
    0.75
    koneksi
    0.75
     agen
    0.75
    ру
    0.75
     Donne
    0.75
    ческому
    0.74
     tern
    0.74
    Activations Density 0.024%

    No Known Activations