© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102675
    Prev
    Next
    INDEX
    Explanations

    describing substances or colors

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

    The neuron specifically detects occurrences of the preposition “of.”

    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
     คา
    -1.97
     you
    -1.95
    {
    -1.91
    ⢪
    -1.79
    菝
    -1.77
    皷
    -1.75
    쨩
    -1.74
     governador
    -1.62
    🧐
    -1.61
    '';
    -1.59
    POSITIVE LOGITS
     that
    2.31
     also
    2.17
    what
    1.89
    olução
    1.70
     could
    1.67
     perhaps
    1.66
     maybe
    1.65
    arrollo
    1.65
     sometimes
    1.63
    ământ
    1.63
    Activations Density 0.044%

    No Known Activations