© 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. 123513
    Prev
    Next
    INDEX
    Explanations

    probabilistic, fluorescent, capacitive

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

    The neuron highly activates on the term “probabilistic” (and close variants) in technical contexts.

    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
    h
    -2.80
    t
    -2.53
     we
    -2.44
     \"
    -2.31
     Reſ
    -2.28
     penchant
    -2.13
     .......
    -2.09
    
    -2.09
     !!!!
    -2.06
     !!!!!
    -2.06
    POSITIVE LOGITS
    玙
    3.09
    ༔
    2.70
    ﾈ
    2.61
    ászló
    2.42
    ！！”
    2.34
     вла
    2.33
     號
    2.25
    !”
    2.25
     報
    2.25
     Weiterbildung
    2.23
    Activations Density 0.005%

    No Known Activations