© 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. 107370
    Prev
    Next
    INDEX
    Explanations

    mathematics and code snippets

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

    This neuron identifies technical “keywords” and command tokens used in code or markup (e.g. programming keywords like import and markup/LaTeX commands like array and left).

    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
     came
    -0.84
     Alone
    -0.72
     against
    -0.72
     to
    -0.71
     Once
    -0.70
     pre
    -0.69
    ต้อง
    -0.69
     As
    -0.68
    angkap
    -0.68
    mão
    -0.68
    POSITIVE LOGITS
    TOO
    0.89
     veranstal
    0.86
     математи
    0.86
     Confession
    0.85
     australiano
    0.85
    urem
    0.84
     manifestly
    0.84
     Arithmetic
    0.83
    oubted
    0.82
     mathématiques
    0.81
    Activations Density 0.000%

    No Known Activations