© 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. 83776
    Prev
    Next
    INDEX
    Explanations

    5 min

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

    The neuron fires on multi‐digit numerical tokens (i.e. numbers) 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
    bilen
    -0.83
    मन
    -0.80
     Zidane
    -0.76
    AddColumn
    -0.76
    muting
    -0.74
     Chara
    -0.72
     قسم
    -0.71
     Zav
    -0.71
     Gunn
    -0.71
     широ
    -0.71
    POSITIVE LOGITS
     Twice
    0.85
    isissez
    0.81
    geri
    0.77
    ėd
    0.76
     percol
    0.74
    netto
    0.74
    hep
    0.73
     katkı
    0.73
    arot
    0.72
     cuticle
    0.72
    Activations Density 0.011%

    No Known Activations