© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117614
    Prev
    Next
    INDEX
    Explanations

    menus, options, west bank, copyright

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

    The neuron responds to number‐bearing tokens—both digit sequences (e.g. “520”, “1184”, “736”) and spelled‐out numerals like “one.”

    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
    まって
    -0.73
    낭
    -0.72
     Ovid
    -0.72
     Optimize
    -0.69
    سوب
    -0.68
     omicron
    -0.66
    GetError
    -0.66
     omega
    -0.65
     '/':
    -0.63
    ⬆
    -0.63
    POSITIVE LOGITS
     компен
    0.78
    ragma
    0.78
    モト
    0.75
    ilov
    0.73
     experimental
    0.72
    ajiban
    0.71
    RESOLVED
    0.71
    pAd
    0.69
    ற்க
    0.69
    STYLE
    0.69
    Activations Density 0.067%

    No Known Activations