© 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. 56743
    Prev
    Next
    INDEX
    Explanations

    programming modes and types

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

    The neuron fires on code‐metadata lines and tokens—things like script filenames (e.g. “Chart.js”), editor mode declarations (e.g. “Mode: C++”), and license header terms—i.e. metadata about code files rather than code logic itself.

    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
    :%.
    -0.97
     motivo
    -0.91
    férences
    -0.88
    grained
    -0.87
    🏫
    -0.84
     provincie
    -0.84
     personale
    -0.84
    beh
    -0.83
    ෆ
    -0.83
    ajaran
    -0.82
    POSITIVE LOGITS
     причем
    0.85
    albeit
    0.85
     навіть
    0.82
    ではでは
    0.79
    付属品
    0.79
    夏休み
    0.78
    Raising
    0.77
     originalmente
    0.77
    ではまた
    0.77
      “
    0.76
    Activations Density 0.705%

    No Known Activations