© 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. 22-GEMMASCOPE-RES-131K
    7. 27650
    Prev
    Next
    INDEX
    Explanations

    contrast or exception

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

    This neuron detects the adversative conjunction “but” when it introduces a contrasting clause.

    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
     and
    -2.55
    ᵗ
    -2.33
    镡
    -2.23
    <td>
    -2.13
    蜕
    -2.05
    béco
    -2.02
    idk
    -1.99
    ooooo
    -1.99
    oooooo
    -1.98
    ły
    -1.94
    POSITIVE LOGITS
     it
    3.59
     there
    3.53
     when
    3.00
     that
    2.66
     since
    2.59
     we
    2.53
     they
    2.52
     with
    2.52
     this
    2.50
    '
    2.45
    Activations Density 0.162%

    No Known Activations