© 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. 85309
    Prev
    Next
    INDEX
    Explanations

    Barrow, Derry, Marietta, Giuliani

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

    The neuron is detecting tokens that are parts of named entities—especially organization names and geographic/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
    寕
    -2.72
    𖣘
    -2.45
    点的
    -2.34
    z
    -2.28
    厛
    -2.22
    hướng
    -2.19
    嗞
    -2.19
    y
    -2.17
    可以
    -2.13
    Зно
    -2.13
    POSITIVE LOGITS
     outras
    2.83
    ists
    2.34
    两年
    2.28
    2.22
     músicos
    2.13
    坨
    2.08
     altre
    2.08
    S
    2.06
    ].
    2.00
    琊
    1.95
    Activations Density 0.003%
    No Known Activations