© 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. 38113
    Prev
    Next
    INDEX
    Explanations

    double _ [noun]

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

    The neuron fires on size or quantity qualifiers in real‐estate feature descriptions—tokens like “double,” “dual,” “king,” or “single” that specify multiple or large‐scale fixtures.

    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
     crept
    -0.89
    大量的
    -0.85
     captiv
    -0.75
     Sorry
    -0.73
     combinations
    -0.72
     teeming
    -0.72
     shuff
    -0.71
    但这
    -0.71
    сього
    -0.71
     unavoid
    -0.71
    POSITIVE LOGITS
     sized
    1.12
     width
    1.04
     ended
    1.00
     occupancy
    0.98
    width
    0.93
    Width
    0.91
     litro
    0.89
     sided
    0.89
    getWidth
    0.88
     sze
    0.88
    Activations Density 0.014%

    No Known Activations