© 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. 39435
    Prev
    Next
    INDEX
    Explanations

    prism, limelight, Pisa

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

    The neuron strongly activates on proper names and specialized terms—i.e. distinct named entities.

    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
    ”
    -3.28
    .”
    -2.75
     he
    -2.72
     również
    -2.70
    ’
    -2.63
    できる
    -2.45
     те
    -2.38
     meager
    -2.34
     Occasionally
    -2.30
     aktuellen
    -2.28
    POSITIVE LOGITS
    鬭
    3.42
    嫱
    2.95
    猡
    2.86
    蕯
    2.78
     menyen
    2.73
    Ꮸ
    2.70
     truk
    2.67
    嗞
    2.64
     短发
    2.59
    硨
    2.59
    Activations Density 0.002%

    No Known Activations