© 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. 83862
    Prev
    Next
    INDEX
    Explanations

    dice

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

    The neuron strongly activates on occurrences of the token “dice” (and its capitalized and “diced” variants).

    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
    <em>
    -3.06
     Saltar
    -2.64
    </h4>
    -2.63
     \\
    -2.63
    </h5>
    -2.59
    For
    -2.45
     However
    -2.45
    <blockquote>
    -2.41
     –
    -2.41
     Many
    -2.36
    POSITIVE LOGITS
     assists
    2.63
     aktive
    2.55
    崀
    2.50
    鋱
    2.50
     ก็
    2.47
     tackles
    2.45
     haar
    2.41
     concentrado
    2.41
    ubahan
    2.36
    Karakteristik
    2.36
    Activations Density 0.001%

    No Known Activations