© 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. 90527
    Prev
    Next
    INDEX
    Explanations

    list item and colon separation

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

    This neuron detects JSON-style object property declarations—i.e. quoted field names (and the following colon) in JSON-like data.

    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
    fh
    -0.85
     Zul
    -0.81
    ellemző
    -0.78
    писки
    -0.77
    Evaluator
    -0.77
    agem
    -0.76
    ஸ
    -0.75
     deſt
    -0.75
     продукт
    -0.74
     всего
    -0.73
    POSITIVE LOGITS
    Tarifs
    0.82
    Spéc
    0.82
     čtyř
    0.79
    tivis
    0.79
    Fow
    0.76
    افر
    0.75
    )+"
    0.73
    modelos
    0.73
     cohé
    0.71
    Accès
    0.71
    Activations Density 0.004%

    No Known Activations