© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74177
    Prev
    Next
    INDEX
    Explanations

    owner of account or role

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

    The neuron activates on occurrences of the term “owner” (e.g. as a field, tag, or identifier) in code or markup contexts.

    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
     are
    -2.28
    “
    -2.11
     about
    -2.02
     said
    -1.97
    )
    -1.84
    '
    -1.77
     '
    -1.74
     naturalmente
    -1.73
    </h5>
    -1.71
    </b>
    -1.70
    POSITIVE LOGITS
    ÍNDICE
    2.30
    CAPITULO
    2.11
    电视台
    1.93
    馒头
    1.91
     dizzy
    1.91
    古风
    1.91
     piş
    1.90
    荸
    1.89
    Pgina
    1.89
    FOREWORD
    1.88
    Activations Density 0.007%

    No Known Activations