© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 50284
    Prev
    Next
    INDEX
    Explanations

    balancing operations

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

    This neuron detects heavily indented code lines—i.e. sequences of leading spaces or tabs indicating deep code nesting.

    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
    zheim
    -0.82
     että
    -0.77
    ulare
    -0.77
     aján
    -0.73
    uples
    -0.69
    stě
    -0.69
    ultur
    -0.69
    ónimo
    -0.68
     Reaper
    -0.68
    otyping
    -0.68
    POSITIVE LOGITS
     balance
    1.02
     балан
    1.02
    balance
    1.02
     rotate
    0.83
    getColor
    0.80
     balancing
    0.75
     imbalance
    0.75
     case
    0.74
     caso
    0.73
     ति
    0.73
    Activations Density 0.006%

    No Known Activations