© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108392
    Prev
    Next
    INDEX
    Explanations

    as followed by a title or role

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

    The neuron fires on past-tense career‐role phrases and job‐title contexts (e.g. “worked,” “was,” “National Coordinator for the…”).

    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
     who
    -1.08
    これから
    -1.07
    新しい
    -1.07
    纐
    -1.05
     schuhe
    -1.04
    えもん
    -1.03
     бухгал
    -1.02
    
    -1.01
     müh
    -1.00
    immen
    -0.99
    POSITIVE LOGITS
     editor
    1.45
     president
    1.31
     faculty
    1.23
     President
    1.18
     director
    1.09
     Editor
    1.09
     owner
    1.08
     founding
    1.07
     district
    1.06
     editorial
    1.05
    Activations Density 0.087%

    No Known Activations