© 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. 104579
    Prev
    Next
    INDEX
    Explanations

    method and apparatus

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

    The neuron activates on the technical term “apparatus.”

    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
    ⩴
    -2.64
    脔
    -2.44
    
    -2.30
    沵
    -2.25
     améli
    -2.23
    翃
    -2.23
    苙
    -2.19
     absorción
    -2.16
    every
    -2.14
     felices
    -2.13
    POSITIVE LOGITS
     Ironically
    2.47
     However
    2.27
     Since
    2.25
     Another
    2.23
     Despite
    2.20
     Interestingly
    2.17
    :
    2.13
     There
    2.11
     Surprisingly
    2.09
     Although
    2.08
    Activations Density 0.012%

    No Known Activations