© 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. 85453
    Prev
    Next
    INDEX
    Explanations

    official commissions

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

    The neuron activates on the word “Commission,” marking mentions of organizations or bodies whose names end with “Commission.”

    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
    僦
    -2.97
     家居
    -2.81
    ᠂
    -2.69
    𖣘
    -2.58
    硨
    -2.53
    湉
    -2.53
    垰
    -2.53
    奩
    -2.53
     continually
    -2.47
     置物
    -2.47
    POSITIVE LOGITS
    ↵↵
    2.52
    ing
    2.48
    g
    2.45
    灕
    2.38
    </td>
    2.34
    笕
    2.30
    狆
    2.27
    "]
    2.23
     самый
    2.13
     februari
    2.08
    Activations Density 0.004%

    No Known Activations