© 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. 48064
    Prev
    Next
    INDEX
    Explanations

    numbers involving hundred

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

    The neuron detects spelled-out numerical quantity expressions (e.g. “one hundred and twenty-five”) 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
    アーカイブ
    -0.77
     Thri
    -0.75
     গ
    -0.75
     burdened
    -0.73
     Lover
    -0.72
    ふれ
    -0.70
    configured
    -0.70
    freopen
    -0.69
    间隔
    -0.69
     sca
    -0.68
    POSITIVE LOGITS
     seventy
    1.30
     fifty
    1.27
     and
    1.27
     eighty
    1.26
     sixty
    1.20
     forty
    1.12
     ninety
    1.10
    andten
    1.08
     thirty
    1.03
     Sixty
    0.94
    Activations Density 0.038%

    No Known Activations