© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 76512
    Prev
    Next
    INDEX
    Explanations

    contrast or exception

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

    The neuron fires on occurrences of the 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_34/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
    -2.52
    蕖
    -1.86
    )();
    -1.82
    )});
    -1.82
    archiwizowane
    -1.77
    vejec
    -1.76
    istice
    -1.67
    ⃰
    -1.66
     légèrement
    -1.64
     presque
    -1.63
    POSITIVE LOGITS
     since
    3.97
     it
    3.89
     there
    3.56
     when
    3.45
     if
    3.39
     with
    3.13
     because
    3.08
     for
    2.97
     after
    2.77
     during
    2.73
    Activations Density 0.159%

    No Known Activations