© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102674
    Prev
    Next
    INDEX
    Explanations

    programming exceptions

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

    references to exceptions in programming contexts, particularly when exceptions are being caught, thrown, or handled in code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    。」
    -1.55
     alluring
    -1.52
    ότη
    -1.51
     hóspedes
    -1.46
     '';
    -1.46
     監督
    -1.44
     astonishing
    -1.41
    postsleuth
    -1.41
    籽
    -1.41
     состояния
    -1.40
    POSITIVE LOGITS
     two
    1.69
    What
    1.56
    جين
    1.53
     雙
    1.52
    ון
    1.51
    هاز
    1.50
    {
    1.50
    Much
    1.50
     dotyczące
    1.49
    <
    1.48
    Activations Density 0.032%

    No Known Activations