© 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. 55940
    Prev
    Next
    INDEX
    Explanations

    code directives and identifiers

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

    The neuron flags tokens typical of programming code—especially Objective-C header/file identifiers and class names.

    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
     moved
    -0.80
     waited
    -0.78
    しかない
    -0.77
    octubre
    -0.76
     betting
    -0.74
     instrucción
    -0.72
     gikk
    -0.71
    맑
    -0.69
     profoundly
    -0.69
     Pent
    -0.69
    POSITIVE LOGITS
     اپل
    1.03
    ANNUAL
    0.77
     枝
    0.75
     proponents
    0.73
    セント
    0.72
     Faker
    0.71
     arrang
    0.71
    faker
    0.71
     kant
    0.71
    姝
    0.70
    Activations Density 0.011%

    No Known Activations