© 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. 54154
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

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

    The neuron selectively activates on multi‐digit numeric tokens (long digit sequences) in the text.

    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
    3
    -1.18
    4
    -0.89
    三次
    -0.84
    有三
    -0.83
    5
    -0.81
     triples
    -0.81
    藜
    -0.81
     tripled
    -0.80
    ³
    -0.80
     thrice
    -0.78
    POSITIVE LOGITS
    २
    1.13
    ૨
    1.12
    ２
    1.09
    ②
    1.09
     два
    1.07
     kedua
    1.06
     two
    1.06
    ২
    1.05
    Second
    1.05
     دوم
    1.04
    Activations Density 0.055%

    No Known Activations