© 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. 22-GEMMASCOPE-RES-131K
    7. 36684
    Prev
    Next
    INDEX
    Explanations

    not... but also

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

    The neuron specifically detects occurrences of the coordinating conjunction “but.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     there
    -2.28
     it
    -2.06
     you
    -1.99
     they
    -1.73
     fiabilidad
    -1.55
     desactivar
    -1.46
     almacenar
    -1.42
    hộp
    -1.40
     we
    -1.38
     fonctionne
    -1.38
    POSITIVE LOGITS
     also
    2.03
     a
    1.77
     "
    1.70
     to
    1.58
     an
    1.56
    '
    1.55
     with
    1.55
    --
    1.49
    That
    1.47
    W
    1.45
    Activations Density 0.012%

    No Known Activations