© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93870
    Prev
    Next
    INDEX
    Explanations

    row and column

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

    The neuron activates on programming code snippets, especially C‐/Java‐style type and control‐structure tokens (e.g. int, boolean, class, new, for, array dimensions).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    thebibliography
    -0.81
    험
    -0.77
    brates
    -0.76
     bescher
    -0.75
    logisch
    -0.74
    results
    -0.73
    дати
    -0.71
    young
    -0.71
    liang
    -0.69
    драв
    -0.69
    POSITIVE LOGITS
     row
    4.50
     rows
    4.06
     column
    3.73
     columns
    3.53
    Row
    3.53
     Row
    3.50
    row
    3.23
     Rows
    3.08
    column
    2.95
     Column
    2.92
    Activations Density 0.098%

    No Known Activations