© 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. 22-GEMMASCOPE-RES-131K
    7. 69284
    Prev
    Next
    INDEX
    Explanations

    adsbygoogle by

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

    The neuron is detecting leading indentation (runs of whitespace at the start of code lines).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     useSelector
    -1.00
    JTable
    -0.89
    another
    -0.89
    strando
    -0.86
    瞰
    -0.82
     combinación
    -0.82
     utilización
    -0.80
     builds
    -0.79
     another
    -0.78
    trá
    -0.78
    POSITIVE LOGITS
     adjustments
    0.95
     adjusting
    0.90
     adjust
    0.90
    修改
    0.86
     modifications
    0.84
     adjustment
    0.84
    调整
    0.80
     changes
    0.79
     alcune
    0.78
    使其
    0.78
    Activations Density 0.056%

    No Known Activations