© 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. 100178
    Prev
    Next
    INDEX
    Explanations

    office locations and roles

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

    This neuron flags occurrences of the word “office” (and closely related forms) in the text.

    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
    
    -2.19
    archiwizowane
    -2.16
     Dingen
    -2.11
     sklep
    -2.09
    誒
    -2.05
    ଢ
    -2.05
    
    -2.03
     mooie
    -1.98
    䜣
    -1.98
     botões
    -1.97
    POSITIVE LOGITS
    d
    2.94
    p
    2.39
    m
    2.19
    ;
    2.17
    店的
    2.13
    io
    2.06
    ↵↵
    2.05
    ен
    2.02
    ?」
    1.95
    k
    1.95
    Activations Density 0.032%

    No Known Activations