© 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. 99572
    Prev
    Next
    INDEX
    Explanations

    urls and paths

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

    The neuron activates on numerical tokens (especially decimals and integers), i.e. it detects 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_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
     being
    -1.51
     acoged
    -1.50
     следующий
    -1.46
    ではなく
    -1.43
    をします
    -1.41
    endif
    -1.41
     already
    -1.39
    を高
    -1.36
     presently
    -1.35
    が必要です
    -1.35
    POSITIVE LOGITS
     to
    2.06
     but
    1.59
     jejich
    1.55
     البته
    1.52
    homonymie
    1.45
     actionTypes
    1.45
     gepub
    1.38
    薮
    1.37
     leurs
    1.36
     berbagai
    1.36
    Activations Density 0.313%

    No Known Activations