© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112757
    Prev
    Next
    INDEX
    Explanations

    "different" followed by a noun

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

    The main thing this neuron does is detect occurrences of the word “different.”

    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
     konkret
    -2.95
     cette
    -2.77
     современного
    -2.75
    ༷
    -2.67
     Quando
    -2.63
    eſ
    -2.55
     
    -2.47
    說
    -2.45
    ウイ
    -2.45
     современных
    -2.42
    POSITIVE LOGITS
    ).
    3.66
    vantaged
    3.00
     That
    2.98
    стреча
    2.86
    髏
    2.84
    
    2.78
    borderSide
    2.72
    новь
    2.69
     zealand
    2.69
    торая
    2.64
    Activations Density 0.073%

    No Known Activations