© 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. 59621
    Prev
    Next
    INDEX
    Explanations

    Dean followed by a name

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

    The neuron fires specifically on occurrences of the proper name “Dean.”

    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
     будут
    -2.84
     Vertreter
    -2.77
    真的好
    -2.63
     Bekannt
    -2.52
     dysfunctional
    -2.52
    iacute
    -2.50
    正常的
    -2.44
    
    -2.42
    ឵
    -2.42
     geniş
    -2.41
    POSITIVE LOGITS
    B
    3.31
    o
    3.05
    ኧ
    3.03
    {
    2.92
    <td>
    2.56
    鵟
    2.56
    </td>
    2.45
    '
    2.44
     vaksin
    2.36
    ahh
    2.34
    Activations Density 0.004%

    No Known Activations