© 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. 81143
    Prev
    Next
    INDEX
    Explanations

    code and programming terms

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

    The neuron consistently fires on standalone code identifier tokens (variable, function, or parameter names) in source code.

    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
     ১
    -0.85
    atelle
    -0.85
     gefeiert
    -0.84
    >';
    -0.84
     Kennt
    -0.81
    тература
    -0.81
     उत्तर
    -0.78
    会社
    -0.76
    !';
    -0.76
     pendidikan
    -0.75
    POSITIVE LOGITS
    掉的
    1.02
    ostante
    0.92
    деров
    0.85
     Crawley
    0.84
     какого
    0.82
    过的
    0.81
    かもしれません
    0.81
     امریک
    0.79
     sådan
    0.78
    such
    0.77
    Activations Density 0.001%

    No Known Activations