© 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. 65550
    Prev
    Next
    INDEX
    Explanations

    quantifiers followed by numbers

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

    The neuron activates on tokens that represent numbers or numeric values (i.e. any token containing digits).

    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
     people
    -0.84
    三千
    -0.80
    dą
    -0.79
    dijo
    -0.77
    五日
    -0.75
     tappa
    -0.75
    hauser
    -0.73
     bote
    -0.73
     millon
    -0.73
    話題
    -0.73
    POSITIVE LOGITS
     dozens
    4.47
     dozen
    4.34
     деся
    3.34
    dozen
    3.19
     decenas
    3.16
     hundreds
    3.06
     dizaines
    3.02
    hundreds
    2.92
     tens
    2.77
    Hundreds
    2.63
    Activations Density 0.106%

    No Known Activations