© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16579
    Prev
    Next
    INDEX
    Explanations

    states and outcomes

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

    This neuron selectively identifies past‐tense or past‐participle verbs ending in “-ed.”

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
    Negative Logits
     swoich
    -1.09
     its
    -1.09
     odası
    -1.03
     borboleta
    -1.03
    الله
    -1.01
     своих
    -1.00
     swojego
    -0.96
     oamen
    -0.95
    Trước
    -0.95
    тивно
    -0.94
    POSITIVE LOGITS
     at
    1.32
     japonaise
    1.05
     africaine
    1.02
     chinoise
    1.02
     niego
    1.02
     froide
    1.01
     innego
    0.98
     everywhere
    0.98
     there
    0.96
     from
    0.93
    Activations Density 0.120%

    No Known Activations