© 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. 7287
    Prev
    Next
    INDEX
    Explanations

    "then" instead of "than"

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

    This neuron does not detect or respond to any specific tokens—it remains inactive across all inputs.

    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
     также
    -2.08
     bahwa
    -2.02
    $
    -2.00
    2
    -2.00
    </th>
    -1.95
    e
    -1.95
    }
    -1.94
    '
    -1.94
    7
    -1.90
    ,”
    -1.82
    POSITIVE LOGITS
    
    1.96
    していた
    1.91
     evaluaciones
    1.84
    ♱
    1.84
     znamená
    1.83
     lecciones
    1.83
    媄
    1.74
    をかける
    1.73
     respuestas
    1.72
     ayakkab
    1.71
    Activations Density 0.005%

    No Known Activations