© 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. 103625
    Prev
    Next
    INDEX
    Explanations

    task completion status

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

    The neuron is basically a “code detector” – it lights up on programming‐language tokens (class names, braces, imports, code identifiers, etc.) rather than on ordinary prose.

    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
     farine
    -0.87
    ٩
    -0.87
     слова
    -0.86
     指輪
    -0.85
    филь
    -0.85
    madd
    -0.83
     Ade
    -0.83
     accede
    -0.81
    ndorf
    -0.81
     incroyable
    -0.81
    POSITIVE LOGITS
     run
    1.95
     execution
    1.84
     finished
    1.82
     running
    1.80
     success
    1.77
     completed
    1.73
     completion
    1.66
     results
    1.62
     successful
    1.59
     failure
    1.59
    Activations Density 0.058%

    No Known Activations