© 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. 60511
    Prev
    Next
    INDEX
    Explanations

    code exception handling

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

    This neuron flags code‐style tokens—especially CamelCase or PascalCase identifiers (like exception and attribute names) and standalone numbers/time markers.

    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
    誦
    -0.96
     około
    -0.90
     retira
    -0.85
     obti
    -0.85
     salga
    -0.85
    にほん
    -0.84
    jść
    -0.84
     公司
    -0.84
     vejo
    -0.84
     moletom
    -0.83
    POSITIVE LOGITS
     e
    2.41
    e
    1.25
     |
    1.04
     ex
    0.92
     excepción
    0.91
     linkovi
    0.89
     alojamientos
    0.88
     hoặc
    0.88
     ei
    0.88
     ea
    0.87
    Activations Density 0.001%

    No Known Activations