© 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. 22-GEMMASCOPE-RES-131K
    7. 129264
    Prev
    Next
    INDEX
    Explanations

    This neuron detects the phrase “but not exclusively.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    but not exclusively

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     but
    -1.20
     mueble
    -1.15
     però
    -1.14
     kuitenkin
    -1.14
     rompecabezas
    -1.09
     agujero
    -1.09
     colchón
    -1.07
     však
    -1.06
    のではない
    -1.05
    ("").
    -1.04
    POSITIVE LOGITS
    అ
    0.90
     المزيد
    0.86
    çoit
    0.86
    హ
    0.83
    చ
    0.83
    nių
    0.83
     bArr
    0.81
    الح
    0.80
     例
    0.80
    englanniksi
    0.80
    Activations Density 0.036%

    No Known Activations