© 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. 97935
    Prev
    Next
    INDEX
    Explanations

    code imports and definitions

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

    This neuron detects programming‐language tokens—especially punctuation and identifiers in code such as dots (.), underscores (_), and import/include keywords.

    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
    FXML
    -0.84
    pubs
    -0.75
     تف
    -0.74
    珈
    -0.73
    ushort
    -0.70
     kya
    -0.70
    ellees
    -0.70
    了吗
    -0.69
    要
    -0.69
    emin
    -0.69
    POSITIVE LOGITS
     functional
    0.94
     espacial
    0.92
     claus
    0.90
    functional
    0.89
     operative
    0.88
     Functional
    0.88
    ェ
    0.83
    Ata
    0.81
     Sien
    0.81
     weight
    0.79
    Activations Density 0.004%

    No Known Activations