© 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. 84484
    Prev
    Next
    INDEX
    Explanations

    foreign accents and names

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

    The neuron strongly activates on programming‐related identifiers—especially class names, module/library names, and other CamelCase or API‐specific tokens in 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
    両方
    -0.85
    的新
    -0.82
     heaving
    -0.80
    频
    -0.80
     culvert
    -0.80
    恢復
    -0.78
    ("")
    -0.76
     zentral
    -0.75
     Moderately
    -0.75
    Ouest
    -0.75
    POSITIVE LOGITS
    Czytaj
    0.89
     utiliz
    0.81
     ı
    0.81
    앤
    0.80
     ๆ
    0.79
     Legend
    0.78
    Fingers
    0.78
     Yard
    0.78
    ocities
    0.78
     garda
    0.77
    Activations Density 0.121%

    No Known Activations