© 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. 10-GEMMASCOPE-RES-131K
    4. 99741
    Prev
    Next
    INDEX
    Explanations

    consequences of actions or events

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

    The neuron fires on numeric expressions—tokens representing numbers (digits or number words) and the surrounding numeric references.

    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
     where
    -1.87
     when
    -1.83
     if
    -1.79
     for
    -1.59
     best
    -1.57
     support
    -1.52
    ’
    -1.48
     how
    -1.44
     always
    -1.41
     general
    -1.40
    POSITIVE LOGITS
     soulign
    1.54
    voyez
    1.54
     piaci
    1.53
     egenskaper
    1.52
     verhind
    1.50
     ekolog
    1.47
     页面
    1.47
     spannend
    1.44
     pengar
    1.43
    蹕
    1.43
    Activations Density 0.124%

    No Known Activations