© 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. 57410
    Prev
    Next
    INDEX
    Explanations

    chart positions and rankings

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

    The neuron fires on numeric and ranking tokens—especially chart positions, years, and other digits conveying stats.

    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
    優勝
    -0.88
    雾
    -0.75
     xong
    -0.74
     künftig
    -0.74
    年から
    -0.71
     by
    -0.71
    HEARING
    -0.71
    aS
    -0.70
    となる
    -0.68
     ملف
    -0.68
    POSITIVE LOGITS
     charts
    2.42
     chart
    2.25
     Billboard
    2.02
     Charts
    1.93
    charts
    1.81
    Chart
    1.80
    chart
    1.80
    Charts
    1.77
     Chart
    1.77
    Billboard
    1.65
    Activations Density 0.064%

    No Known Activations