© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129638
    Prev
    Next
    INDEX
    Explanations

    if the

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

    This neuron fires on words that introduce comparisons or similes (e.g. “like,” “as if,” “as you might expect”).

    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
    "));
    -1.75
    ַע
    -1.69
    
    -1.66
     is
    -1.64
    ",
    -1.60
    "))
    -1.56
     creada
    -1.55
    玬
    -1.54
    !")
    -1.54
     to
    -1.54
    POSITIVE LOGITS
     
    1.55
    ↵
    1.53
    0
    1.48
     THEY
    1.38
    ’
    1.34
     a
    1.33
     nahmen
    1.31
     нашел
    1.31
     вони
    1.29
     «
    1.28
    Activations Density 0.013%

    No Known Activations