© 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. 34-GEMMASCOPE-RES-131K
    7. 47200
    Prev
    Next
    INDEX
    Explanations

    Ply- and cly- prefixes

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

    words containing "ly" like "Plymouth", "Clyde", and "ply".

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi

    The neuron fires on tokens containing the letter sequence “ly.”

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     SUD
    -0.75
    くれない
    -0.73
    kowa
    -0.72
     surrounds
    -0.72
    Volunteer
    -0.71
     shea
    -0.71
     SMD
    -0.70
     roo
    -0.70
    였다
    -0.70
    還是
    -0.70
    POSITIVE LOGITS
    timg
    0.85
    ometric
    0.85
     Fly
    0.82
     vodu
    0.80
    adomo
    0.80
    blown
    0.80
    mouth
    0.79
    Engineers
    0.79
     delà
    0.78
    lihood
    0.77
    Activations Density 0.013%

    No Known Activations