© 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. 21540
    Prev
    Next
    INDEX
    Explanations

    Johnston, Johnstone, Johnstown

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

    The neuron detects capitalized proper names (people’s surnames and place names).

    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
    i
    -2.91
     ''
    -2.89
    AN
    -2.78
    ''
    -2.67
    with
    -2.64
    AT
    -2.47
    Ꮟ
    -2.45
    AL
    -2.42
    '.
    -2.39
    or
    -2.38
    POSITIVE LOGITS
     untuk
    2.78
    zeniem
    2.75
    玙
    2.72
    .
    2.58
    鹛
    2.53
    什么呢
    2.48
    鸶
    2.44
    嫆
    2.41
     để
    2.39
    новь
    2.34
    Activations Density 0.002%

    No Known Activations