© 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. 58870
    Prev
    Next
    INDEX
    Explanations

    listing properties and components

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

    The neuron strongly activates on the conjunction “and” when it links two technical or topical terms (e.g. in scientific‐paper titles or headings).

    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
    蕷
    -1.82
    釙
    -1.79
    '
    -1.79
     ของ
    -1.74
    ிய
    -1.64
    檮
    -1.61
    铩
    -1.58
    哢
    -1.58
     Of
    -1.57
    壜
    -1.55
    POSITIVE LOGITS
    3
    2.06
    6
    2.05
    </sup>
    1.88
    _
    1.84
    4
    1.84
    {
    1.79
    8
    1.73
     bunun
    1.71
    0
    1.69
    7
    1.64
    Activations Density 0.221%

    No Known Activations