© 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. 44132
    Prev
    Next
    INDEX
    Explanations

    job roles and descriptions

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

    The neuron activates on words naming occupations or professional roles.

    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
    tedrale
    -1.62
    ığınız
    -1.34
     definitive
    -1.32
     ਵਿੱਚ
    -1.31
     nonstop
    -1.30
    productId
    -1.29
    isesti
    -1.28
     bereits
    -1.27
     bigger
    -1.26
     distanza
    -1.26
    POSITIVE LOGITS
     tà
    1.54
    reen
    1.54
     who
    1.53
    </i>
    1.51
     "
    1.48
    geries
    1.34
     Þ
    1.29
    们
    1.28
     revisa
    1.28
    erees
    1.27
    Activations Density 0.116%

    No Known Activations