© 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. 10-GEMMASCOPE-RES-131K
    7. 21713
    Prev
    Next
    INDEX
    Explanations

    Ya know

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

    The neuron is triggered by number tokens that include a decimal point (i.e. floating-point numerals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    缡
    -2.09
    艫
    -2.08
    他们的
    -2.08
    髕
    -2.02
    呖
    -2.02
     apenas
    -2.00
     mesma
    -1.99
    
    -1.97
    ৬
    -1.95
    憷
    -1.92
    POSITIVE LOGITS
    ጺ
    2.39
     {
    2.06
     ")");
    1.94
    囖
    1.94
    钲
    1.94
    注意事
    1.87
    pecabe
    1.81
    tômes
    1.75
    鶲
    1.73
     referrerpolicy
    1.72
    Activations Density 0.000%

    No Known Activations