© 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. 37858
    Prev
    Next
    INDEX
    Explanations

    set or defined

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

    The neuron fires on code tokens related to error handling—particularly uppercase error identifiers and “not found”/“not set” conditions.

    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
    destroyAll
    -0.83
    idać
    -0.83
     чрез
    -0.79
     inför
    -0.78
    ทั้งหมด
    -0.77
     kanya
    -0.77
    Kast
    -0.76
    نکته
    -0.75
    Invited
    -0.75
     coroner
    -0.73
    POSITIVE LOGITS
     set
    2.63
     defined
    2.44
    Defined
    1.91
    defined
    1.84
     populated
    1.79
     filled
    1.78
     specified
    1.70
    Set
    1.69
     definido
    1.66
    IsSet
    1.66
    Activations Density 0.114%

    No Known Activations