© 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. 83940
    Prev
    Next
    INDEX
    Explanations

    HTML body and script tags

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

    The neuron is detecting runs of leading whitespace (indentation) in code examples.

    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
    ActivityResult
    -0.79
    setImage
    -0.78
    ButtonModule
    -0.74
    šin
    -0.72
     resourceCulture
    -0.71
     Keats
    -0.70
     зерка
    -0.70
    ্ব
    -0.69
    盹
    -0.69
    躇
    -0.68
    POSITIVE LOGITS
     body
    1.70
    body
    1.20
     Body
    1.16
     bodies
    1.13
     bodily
    1.07
    Body
    1.06
    BODY
    0.99
    getBody
    0.98
     Körper
    0.95
     lichaam
    0.90
    Activations Density 0.019%

    No Known Activations