© 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. 23763
    Prev
    Next
    INDEX
    Explanations

    inventory management and code

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

    The neuron strongly activates on programming‐language source code tokens—especially capitalized identifiers (classes, methods, variables) and numeric literals.

    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
     détru
    -0.82
     undulating
    -0.81
     déplo
    -0.79
     jeweiligen
    -0.73
    Kedves
    -0.72
     colaboradores
    -0.72
    dagogik
    -0.71
     blinded
    -0.70
     entspan
    -0.70
    Шу
    -0.69
    POSITIVE LOGITS
     boh
    0.79
    wreck
    0.79
    പ്
    0.78
     MINUTES
    0.76
    座椅
    0.76
    gle
    0.73
    tracks
    0.73
     septem
    0.72
    nological
    0.71
     StringVar
    0.71
    Activations Density 0.008%

    No Known Activations