© 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. 3771
    Prev
    Next
    INDEX
    Explanations

    passage of something

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

    The neuron activates on numeric tokens—i.e. quantities, measurements, and other numbers appearing 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
    ︕
    -2.02
    硨
    -1.93
     広場
    -1.91
     eme
    -1.80
    yelitis
    -1.80
     CENTRO
    -1.77
     mib
    -1.77
     Komis
    -1.77
     abstracto
    -1.77
    🤠
    -1.74
    POSITIVE LOGITS
    
    2.66
    ↵
    2.58
     Traditionally
    2.48
     Importantly
    2.41
     Regarding
    2.36
     Significantly
    2.34
     Fundament
    2.23
     Nowadays
    2.20
     Gesetze
    2.19
     Ensuring
    2.17
    Activations Density 0.006%

    No Known Activations