© 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. 10-GEMMASCOPE-RES-131K
    4. 61498
    Prev
    Next
    INDEX
    Explanations

    listing multiple things

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

    The neuron activates on numeric tokens—especially decimal numbers—i.e. it spots numerical measurements or quantities.

    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
    ↵
    -2.33
    The
    -1.88
    n
    -1.74
     –
    -1.71
     Their
    -1.66
    トッピング
    -1.59
    
    -1.58
    …………
    -1.57
    ݮ
    -1.54
    <strong>
    -1.51
    POSITIVE LOGITS
    埽
    2.11
    หรือ
    2.03
    或
    1.96
    縢
    1.89
     that
    1.80
     или
    1.80
    ayaquil
    1.79
     everything
    1.78
    และ
    1.76
    🩱
    1.76
    Activations Density 0.048%

    No Known Activations