© 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. 22-GEMMASCOPE-RES-131K
    7. 130107
    Prev
    Next
    INDEX
    Explanations

    The neuron specifically activates on the technical phrase “operating member.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    site

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    攫
    -0.89
    plaats
    -0.87
    zám
    -0.84
    aliyun
    -0.80
    嶽
    -0.77
    lccn
    -0.76
    нено
    -0.73
     siempre
    -0.71
    taxon
    -0.71
    detek
    -0.71
    POSITIVE LOGITS
    今度は
    0.82
     ndani
    0.82
    ləş
    0.82
    uating
    0.81
     appartenant
    0.80
    ente
    0.80
    ICATION
    0.79
    atmosphère
    0.79
    Intérieur
    0.79
    intégration
    0.79
    Activations Density 0.104%

    No Known Activations