© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84940
    Prev
    Next
    INDEX
    Explanations

    former professions

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

    The neuron fires on whitespace and punctuation tokens (commas, periods, and spaces), i.e. on sentence‐ or phrase‐boundary markers.

    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
    preneurs
    -1.02
    lords
    -1.02
    izate
    -1.00
    ients
    -0.95
    cillors
    -0.94
    arians
    -0.94
    tellers
    -0.94
    swire
    -0.94
     [];
    -0.93
    brokers
    -0.93
    POSITIVE LOGITS
     former
    2.67
     veteran
    2.47
    Former
    1.99
     longtime
    1.86
    former
    1.82
     actor
    1.78
     retired
    1.70
     singer
    1.69
     Former
    1.68
     poet
    1.63
    Activations Density 0.294%

    No Known Activations