© 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. 102362
    Prev
    Next
    INDEX
    Explanations

    furniture items

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

    The main thing this neuron does is spot numbers and enumeration markers (e.g. digits, list‐item numerals, section headings).

    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
     Reste
    -0.88
    şiv
    -0.79
     木製
    -0.78
    associazione
    -0.77
    蒾
    -0.76
    ienen
    -0.75
     viewDidLoad
    -0.75
    сайт
    -0.74
    ポーチ
    -0.73
    السلام
    -0.71
    POSITIVE LOGITS
     table
    2.94
     tables
    2.88
     chairs
    2.83
     chair
    2.59
     desk
    2.42
     Tables
    2.25
    Tables
    2.25
     desks
    2.23
     sofa
    2.23
     stool
    2.03
    Activations Density 0.093%

    No Known Activations