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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 120163
    Prev
    Next
    INDEX
    Explanations

    in case you

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

    The neuron specializes in detecting second-person address—instances of the pronoun “you” (and its contracted suffixes).

    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
     both
    -1.80
     TRABAJO
    -1.63
    ociação
    -1.63
     Frühjahr
    -1.59
     něj
    -1.56
     grossly
    -1.54
     each
    -1.53
    </b>
    -1.52
    澳门
    -1.52
    劏
    -1.49
    POSITIVE LOGITS
    ↵
    2.17
     they
    1.99
     какие
    1.81
    {
    1.77
     incluyendo
    1.70
    *,
    1.59
     segn
    1.56
    7
    1.55
    »,
    1.54
     هناك
    1.53
    Activations Density 0.004%

    No Known Activations