© 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. 127585
    Prev
    Next
    INDEX
    Explanations

    you are welcome to

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

    The neuron detects welcoming or invitation language, especially the word “welcome” (often in “welcome to” contexts).

    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
    .$.
    -1.82
    ,}
    -1.71
    ukone
    -1.66
    ratislava
    -1.63
    atasaray
    -1.63
    ()]);
    -1.62
    ecera
    -1.61
    érieures
    -1.60
     Когда
    -1.60
     you
    -1.59
    POSITIVE LOGITS
    d
    1.68
     decât
    1.52
    ve
    1.51
     additional
    1.44
     to
    1.41
    なのですが
    1.39
    N
    1.38
     finnes
    1.38
     however
    1.36
    ic
    1.34
    Activations Density 0.004%

    No Known Activations