© 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. 67231
    Prev
    Next
    INDEX
    Explanations

    then clauses

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

    The neuron fires on numeric tokens or number expressions (digits, percent‐signs, dates/quantities) 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
     høre
    -1.07
    anship
    -1.01
     prøve
    -0.99
     ไม่มี
    -0.91
     tæn
    -0.91
     esquí
    -0.90
    ωμα
    -0.90
    izaron
    -0.88
     importancia
    -0.88
    TODOS
    -0.87
    POSITIVE LOGITS
     then
    1.74
     will
    1.47
     to
    1.45
     wtedy
    1.26
    這樣
    1.24
    then
    1.21
    这样
    1.21
    Then
    1.12
     тогда
    1.12
    จะ
    1.11
    Activations Density 0.034%

    No Known Activations