© 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. 109396
    Prev
    Next
    INDEX
    Explanations

    search and filter

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

    The neuron fires most strongly on programming-style identifiers or parameter/option names (e.g. field names, config keys, function or flag names) in code or technical documentation.

    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
     кно
    -0.81
    児童
    -0.80
     ברו
    -0.76
    /}
    -0.76
    сут
    -0.75
    Stu
    -0.74
    رس
    -0.74
     thiệu
    -0.72
    يب
    -0.71
    uas
    -0.71
    POSITIVE LOGITS
     filter
    0.88
     sear
    0.86
     search
    0.85
     Searching
    0.84
    amélioration
    0.83
    ricated
    0.83
    aumento
    0.81
    predicates
    0.80
    搜索
    0.79
     Sear
    0.77
    Activations Density 0.001%

    No Known Activations