© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66582
    Prev
    Next
    INDEX
    Explanations

    describing transition or sequence

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

    The neuron is activated by numeric tokens and expressions of quantity (e.g. numbers, measures, counts).

    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
     bluz
    -1.34
     eksklu
    -1.26
     nadru
    -1.25
     ekst
    -1.22
     pegat
    -1.13
    slika
    -1.10
    vampire
    -1.09
     対
    -1.09
    assorted
    -1.09
    timberland
    -1.09
    POSITIVE LOGITS
     new
    1.32
     If
    1.28
    It
    1.23
     had
    1.22
    ǀ
    1.16
     if
    1.16
    new
    1.15
    end
    1.15
     when
    1.14
     scheda
    1.12
    Activations Density 0.195%

    No Known Activations