© 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. 115531
    Prev
    Next
    INDEX
    Explanations

    most influential people

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

    The neuron detects numeric tokens or numerical expressions (cardinal and ordinal numbers).

    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
     Championship
    -0.88
    之前
    -0.84
    已
    -0.84
    Interceptor
    -0.84
     romanzo
    -0.83
     Bowden
    -0.82
    大
    -0.79
    Sail
    -0.79
    Де
    -0.77
     می‌گو
    -0.77
    POSITIVE LOGITS
     influence
    1.29
    influence
    1.29
     influência
    1.10
     invloed
    1.08
    影響
    1.02
    的影响
    0.94
    figuras
    0.93
     Influence
    0.93
     influencia
    0.91
    powerful
    0.90
    Activations Density 0.021%

    No Known Activations