© 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. 19452
    Prev
    Next
    INDEX
    Explanations

    Briefs June

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

    The neuron activates on tokens containing numerals (including integers and decimals).

    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
    ⢊
    -2.81
    鋱
    -2.80
     untuk
    -2.78
    𓆜
    -2.73
    .”
    -2.67
    𓆟
    -2.67
    ペーン
    -2.63
    ⮜
    -2.59
    穑
    -2.58
    ﮨ
    -2.56
    POSITIVE LOGITS
     пять
    2.92
     whirl
    2.45
     及
    2.42
     favoriser
    2.38
     десять
    2.36
    ーーーー
    2.34
    Ideally
    2.31
    摭
    2.30
     และ
    2.30
    or
    2.28
    Activations Density 0.010%

    No Known Activations