© 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. 86927
    Prev
    Next
    INDEX
    Explanations

    in fact

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

    The neuron is a comma‐detector, firing strongly on commas (and immediately around them) in the text.

    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
     waarbij
    -0.97
     excelencia
    -0.96
     небольшой
    -0.94
     hormigón
    -0.93
     poiché
    -0.91
     zaradi
    -0.91
    üstet
    -0.90
    Inches
    -0.89
     essendo
    -0.88
    INH
    -0.88
    POSITIVE LOGITS
     in
    4.72
     infatti
    2.89
     actually
    2.59
    Actually
    2.58
     indeed
    2.53
     Actually
    2.41
    actually
    2.41
    実際
    2.41
    事实上
    2.39
    其實
    2.38
    Activations Density 0.081%

    No Known Activations