© 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. 70426
    Prev
    Next
    INDEX
    Explanations

    vin plate, CW show

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

    This neuron activates on technical or product-name terms (e.g. hardware/software names, model or part identifiers, acronyms).

    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
    蓐
    -2.09
    ᠁
    -2.03
    趿
    -2.03
    
    -1.96
    扨
    -1.95
    ⩖
    -1.95
     dè
    -1.91
    螣
    -1.89
    踅
    -1.89
     Dinas
    -1.88
    POSITIVE LOGITS
     Despite
    2.33
     new
    2.17
     three
    2.14
     When
    2.13
     four
    2.11
     Being
    2.09
     With
    2.08
     time
    2.06
     five
    2.06
     After
    2.05
    Activations Density 0.105%

    No Known Activations