© 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. 12249
    Prev
    Next
    INDEX
    Explanations

    bugs and issues

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

    The neuron activates on language used when reporting software defects (e.g. “bug,” “issue,” “glitch,” “error,” “strange”).

    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
     económico
    -0.79
     upaya
    -0.79
    Facts
    -0.79
     Wörter
    -0.76
    >);
    -0.74
    BuilderFactory
    -0.73
     canina
    -0.73
    dighet
    -0.72
    backup
    -0.71
    blich
    -0.71
    POSITIVE LOGITS
     bug
    4.81
     bugs
    4.78
    bug
    3.64
    bugs
    3.55
     Bug
    3.45
    BUG
    3.33
    Bug
    3.33
     Bugs
    3.25
    Bugs
    3.13
     BUG
    2.98
    Activations Density 0.121%

    No Known Activations