© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 45455
    Prev
    Next
    INDEX
    Explanations

    error handling in code

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

    The neuron is tuned to spot numeric literals 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
     Spas
    -0.78
    놓
    -0.75
     precedes
    -0.72
    是非
    -0.70
    marco
    -0.69
     communique
    -0.68
     Jawa
    -0.68
    ленная
    -0.66
    Isla
    -0.66
     marshall
    -0.66
    POSITIVE LOGITS
     prochain
    0.79
     verwende
    0.77
     najwyżs
    0.76
     फिर
    0.76
    ovsk
    0.75
    canonical
    0.70
     czł
    0.69
    ulsory
    0.69
     Schrifts
    0.68
     conduction
    0.67
    Activations Density 0.097%

    No Known Activations