© 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. 40067
    Prev
    Next
    INDEX
    Explanations

    but X

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

    The neuron strongly activates on the conjunction “but,” signaling instances of contrastive “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_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
     there
    -1.67
    .
    -1.65
    uttgart
    -1.56
    Your
    -1.46
    worths
    -1.45
     it
    -1.45
    lántico
    -1.42
    UARIO
    -1.38
    iwisata
    -1.38
    鬟
    -1.37
    POSITIVE LOGITS
     the
    2.27
    }
    1.70
     those
    1.64
    änemark
    1.59
    ′,
    1.52
    :
    1.52
    ellido
    1.50
     infolge
    1.48
    、「
    1.46
     incluyen
    1.44
    Activations Density 0.012%

    No Known Activations