© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 131039
    Prev
    Next
    INDEX
    Explanations

    admin contexts

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

    The neuron activates strongly on occurrences of the exact token “Admin.”

    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
    轳
    -3.41
     Then
    -2.84
    vantaged
    -2.81
     Of
    -2.67
    </em>
    -2.66
    </h4>
    -2.58
     Она
    -2.52
     wodurch
    -2.52
     womit
    -2.48
     Schreiben
    -2.47
    POSITIVE LOGITS
    狆
    3.42
    喁
    2.97
    蹕
    2.92
    ୈ
    2.80
    ed
    2.78
     attaques
    2.66
    蟊
    2.61
    😸
    2.56
    鶲
    2.55
    后
    2.53
    Activations Density 0.005%

    No Known Activations