© 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. 94203
    Prev
    Next
    INDEX
    Explanations

    words ending in -ty

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

    The main thing this neuron does is detect words containing the character sequence “ual,” i.e. adjectives or nouns ending in “-ual” (as in casual, casualty, etc.).

    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
     jste
    -0.79
    udt
    -0.75
     bisnis
    -0.71
    潑
    -0.69
    Estonia
    -0.69
    Nigeria
    -0.69
     Muchas
    -0.69
    Belgium
    -0.69
    wj
    -0.69
    ICR
    -0.68
    POSITIVE LOGITS
    ties
    3.91
    ty
    1.95
    TY
    1.71
    tie
    1.70
    ity
    1.62
    ety
    1.41
    nty
    1.30
    lty
    1.27
    hty
    1.26
    ्टी
    1.26
    Activations Density 0.036%

    No Known Activations