© 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. 98890
    Prev
    Next
    INDEX
    Explanations

    code and programming documentation

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

    The neuron flags isolated technical or markup terms (e.g. class names, CSS keywords, HTML/URL parts, license headers)—in short, code-oriented vocabulary.

    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
    Lateral
    -0.71
     Miguel
    -0.71
    Slug
    -0.71
     angesehen
    -0.70
    Anonymous
    -0.70
    become
    -0.69
    Mitchell
    -0.69
    died
    -0.69
     Whisper
    -0.69
     Haley
    -0.69
    POSITIVE LOGITS
    决
    0.64
    lcccc
    0.63
     Main
    0.63
    对象的
    0.62
     diikuti
    0.62
     paddy
    0.61
    zkopf
    0.61
     after
    0.60
     приготовить
    0.60
    ชั่น
    0.60
    Activations Density 0.061%

    No Known Activations