© 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. 82768
    Prev
    Next
    INDEX
    Explanations

    fields or exclude keywords

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

    This neuron detects indentation tokens (leading spaces) in code blocks.

    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
    ellä
    -0.93
    thorn
    -0.84
    ướ
    -0.81
    එ
    -0.79
    వా
    -0.77
    砺
    -0.77
    شوف
    -0.77
    lawan
    -0.75
    menso
    -0.75
    茁
    -0.74
    POSITIVE LOGITS
     fields
    1.35
    fields
    1.35
     Fields
    1.17
    exclude
    1.13
     field
    1.10
    Fields
    1.09
     FIELDS
    1.02
     exclude
    1.02
    FIELDS
    0.96
     said
    0.90
    Activations Density 0.008%

    No Known Activations