© 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. 10-GEMMASCOPE-RES-131K
    7. 114181
    Prev
    Next
    INDEX
    Explanations

    if you can

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

    This neuron responds to main action verbs—especially the infinitival or base-form verbs that follow modals like “can” or “could.”

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     nawet
    -1.54
    even
    -1.52
     даже
    -1.36
     навіть
    -1.34
     EVEN
    -1.30
     також
    -1.29
    Podob
    -1.29
     but
    -1.28
     SqlDbType
    -1.26
    Dział
    -1.26
    POSITIVE LOGITS
     that
    1.44
    ↵↵
    1.37
     it
    1.12
    ,
    1.11
    ↵↵↵
    1.11
    ↵↵↵↵
    1.09
     overcame
    1.07
    kah
    1.06
     somehow
    1.06
     ...
    1.06
    Activations Density 0.025%

    No Known Activations