© 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. 11898
    Prev
    Next
    INDEX
    Explanations

    java, javascript, python keywords

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

    This neuron detects long runs of whitespace (i.e. heavily indented 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_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
    bių
    -0.80
    地产
    -0.73
     affairs
    -0.72
    weetie
    -0.71
     pře
    -0.69
    ෂ
    -0.69
    illite
    -0.67
    ệu
    -0.66
    neman
    -0.66
    顛
    -0.66
    POSITIVE LOGITS
     layer
    1.52
    layer
    1.44
    Layer
    1.06
     Layer
    1.01
     LAYER
    0.97
    LAYER
    0.96
     parent
    0.93
    parent
    0.92
     layers
    0.91
    Parent
    0.88
    Activations Density 0.007%

    No Known Activations