© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111974
    Prev
    Next
    INDEX
    Explanations

    primary, major, principal, greatest, significant, prime

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

    This neuron activates on words derived from the “principle/principal” root (e.g. principal, primary, fondamentale, principale, etc.).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    <
    -2.67
    ers
    -2.59
    {
    -2.58
    ',
    -2.42
    .
    -2.39
    </th>
    -2.39
    ↵↵
    -2.39
    &
    -2.30
    <i>
    -2.30
    ?
    -2.17
    POSITIVE LOGITS
     ataupun
    3.05
    鹟
    2.77
    ?”
    2.73
    Ꮉ
    2.63
    ⎆
    2.59
    輾
    2.58
    Ꭳ
    2.50
    .”)
    2.48
    鲣
    2.47
    さてさて
    2.44
    Activations Density 0.003%

    No Known Activations