© 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. 39668
    Prev
    Next
    INDEX
    Explanations

    about us, contact us

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

    This neuron activates on website section headings, especially “About Us.”

    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
     ΤΟ
    -1.87
    mici
    -1.78
    geordnet
    -1.77
    ዬ
    -1.77
     this
    -1.76
    yesha
    -1.66
     significativa
    -1.66
     menggunakan
    -1.66
    ではでは
    -1.65
    egis
    -1.63
    POSITIVE LOGITS
    </strong>
    2.48
    d
    2.25
    ↵
    1.95
    \
    1.91
    /
    1.87
    j
    1.83
    .
    1.68
     seiner
    1.61
    ↵↵↵↵↵↵↵↵↵↵
    1.58
    的人都
    1.58
    Activations Density 0.012%

    No Known Activations