© 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. 22-GEMMASCOPE-RES-131K
    7. 68216
    Prev
    Next
    INDEX
    Explanations

    LG has

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

    The neuron detects error‐raising or exception‐throwing statements across different programming languages.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     nowy
    -1.05
    Ngoài
    -0.98
     hydrauli
    -0.91
     péro
    -0.90
    cluding
    -0.88
    matician
    -0.87
     durer
    -0.86
    RICULUM
    -0.86
     rasg
    -0.85
     milho
    -0.84
    POSITIVE LOGITS
     if
    1.41
    if
    1.11
    さんも
    0.95
    ią
    0.92
     если
    0.91
     też
    0.87
     nếu
    0.85
     has
    0.85
    antung
    0.84
     effettu
    0.84
    Activations Density 0.002%

    No Known Activations