© 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. 113340
    Prev
    Next
    INDEX
    Explanations

    flair, flamboyant, flare

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

    The neuron fires on words that denote stylish flair or flamboyant ornamentation (e.g., “flair,” “panache,” “flamboyant,” “flare”).

    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
    玧
    -3.14
    獃
    -2.72
     良品
    -2.64
    
    -2.52
    扨
    -2.50
    s
    -2.44
    d
    -2.42
     ”
    -2.39
     It
    -2.34
    籏
    -2.34
    POSITIVE LOGITS
    .
    2.88
    '
    2.70
     '
    2.44
    ⑊
    2.14
    )
    2.00
    ╽
    1.98
    鸶
    1.97
    ?"
    1.94
    acterísticas
    1.93
    ="
    1.88
    Activations Density 0.001%

    No Known Activations