© 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. 22-GEMMASCOPE-RES-131K
    7. 13307
    Prev
    Next
    INDEX
    Explanations

    multilingual technical content

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

    The neuron strongly activates on numeric tokens (integers or decimals) 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_22/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
     in
    -1.11
    的一個
    -1.05
     it
    -1.05
     isn
    -1.05
     according
    -1.05
    tesis
    -1.04
    oxidants
    -1.04
    caris
    -1.04
     する
    -1.02
     føl
    -1.02
    POSITIVE LOGITS
     queste
    1.28
    توضیحات
    1.23
    These
    1.19
    ㌧
    1.18
     также
    1.18
    illary
    1.13
    Beberapa
    1.11
    Hechos
    1.06
    这两
    1.06
    Yesterday
    1.06
    Activations Density 0.002%

    No Known Activations