© 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. 34-GEMMASCOPE-RES-131K
    7. 117307
    Prev
    Next
    INDEX
    Explanations

    profession turned

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

    The neuron fires strongly on words naming people’s occupations or professional titles.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ß
    -0.97
    eaways
    -0.91
     beteiligt
    -0.82
    oute
    -0.81
     душа
    -0.79
     erreichbar
    -0.78
     pojawi
    -0.77
    avail
    -0.77
    ̚
    -0.75
     zusammen
    -0.75
    POSITIVE LOGITS
     turned
    5.41
    turned
    4.59
     Turned
    3.70
    Turned
    3.70
     TURN
    2.75
     turn
    2.69
    TURN
    2.41
     devenu
    2.38
    turn
    2.36
    Turn
    2.14
    Activations Density 0.080%

    No Known Activations