© 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. 41472
    Prev
    Next
    INDEX
    Explanations

    validity context

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

    The neuron activates on numeric measurements and their context—especially decimal or integer values (e.g. “41.5,” “24.125,” “valid 156,” “for 164,” etc.).

    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
     diversos
    -1.55
    ↵
    -1.52
            
    -1.51
     mientras
    -1.43
     diverses
    -1.41
      
    -1.40
    </strong>
    -1.33
     zwei
    -1.31
    type
    -1.29
     mène
    -1.27
    POSITIVE LOGITS
     for
    1.96
     on
    1.72
    Even
    1.37
    (),
    
    1.27
     विश्वसनीयता
    1.26
    Probably
    1.25
    Regardless
    1.24
    =“
    1.23
    ={
    
    1.23
     Organisationen
    1.20
    Activations Density 0.013%

    No Known Activations