© 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. 11238
    Prev
    Next
    INDEX
    Explanations

    any or every

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

    The neuron detects occurrences of the word “any.”

    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
    possibly
    -1.73
    倅
    -1.67
    鶺
    -1.63
    o
    -1.56
    踯
    -1.55
    
    -1.52
     unſ
    -1.52
    !!!!!!!!!
    -1.52
     connecter
    -1.50
    繻
    -1.48
    POSITIVE LOGITS
     already
    1.87
    之以
    1.73
     found
    1.67
     então
    1.63
     racked
    1.61
     other
    1.60
     tried
    1.59
     also
    1.57
     well
    1.54
     still
    1.52
    Activations Density 0.011%

    No Known Activations