© 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. 102799
    Prev
    Next
    INDEX
    Explanations

    names starting with lucia or lucie

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

    This neuron activates on tokens containing the substring “Luc” (e.g. Lucia, Lucía, Lucie, Lucifer).

    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
    橚
    -3.00
    鱨
    -2.97
    רונות
    -2.92
    鄠
    -2.92
    ⩤
    -2.92
    螃
    -2.89
    怱
    -2.88
    泐
    -2.86
    eſt
    -2.83
    丷
    -2.81
    POSITIVE LOGITS
    .
    4.19
    }
    3.69
    -
    3.48
    </td>
    3.34
    2
    3.00
     -
    2.94
    $
    2.92
    and
    2.64
    ↵↵↵↵↵↵
    2.58
     I
    2.52
    Activations Density 0.002%

    No Known Activations