© 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. 130867
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on standalone numeric tokens (integer values) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    XML elements and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     which
    -1.55
     just
    -1.49
     before
    -1.48
     information
    -1.45
     what
    -1.44
     start
    -1.41
     its
    -1.40
     their
    -1.40
     well
    -1.38
     without
    -1.34
    POSITIVE LOGITS
    粜
    1.33
    ’
    1.31
    ͛
    1.27
     alfo
    1.27
     området
    1.24
     estadounid
    1.23
     おしゃれ
    1.22
    
    1.22
     vanlig
    1.20
     kroppen
    1.20
    Activations Density 0.031%

    No Known Activations