© 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. 98684
    Prev
    Next
    INDEX
    Explanations

    context and describe blocks

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

    This neuron detects leading indentation (whitespace at the start of a line), with stronger activations for deeper nesting (more spaces).

    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
     chinois
    -0.81
     membunuh
    -0.81
    stums
    -0.78
     служи
    -0.77
    žu
    -0.76
    Pré
    -0.76
     curieux
    -0.75
     néer
    -0.73
     batterie
    -0.73
     оформи
    -0.73
    POSITIVE LOGITS
     context
    1.50
     let
    1.33
    context
    1.30
     contexts
    1.15
     Let
    1.06
    let
    1.05
     subject
    1.02
     CONTEXT
    1.00
     contex
    0.95
    WithContext
    0.94
    Activations Density 0.012%

    No Known Activations