© 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. 22-GEMMASCOPE-RES-131K
    7. 128853
    Prev
    Next
    INDEX
    Explanations

    The neuron is detecting past-tense verbs (words ending in “-ed”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    past tense verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     is
    -1.30
     we
    -1.16
     your
    -1.01
     мы
    -0.94
     you
    -0.88
    🏻
    -0.86
     chúng
    -0.84
     것은
    -0.84
     ');
    -0.81
     Fleury
    -0.80
    POSITIVE LOGITS
     was
    1.23
     zostanie
    1.05
    était
    1.04
    Lens
    1.04
     hoped
    1.02
     encontraron
    1.01
     damals
    1.00
    szám
    0.99
     previously
    0.99
     márm
    0.98
    Activations Density 0.093%

    No Known Activations