© 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. 22-GEMMASCOPE-RES-131K
    7. 25144
    Prev
    Next
    INDEX
    Explanations

    Regards followed by punctuation

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

    The neuron fires strongly on email valedictions (sign-off phrases like “Regards,” “Best regards,” “Kind regards,” etc.).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     única
    -1.32
    UIFont
    -1.27
     Asegúrese
    -1.26
    了什么
    -1.25
     berbagai
    -1.23
    ()]);
    -1.23
    ExecuteReader
    -1.22
    aussian
    -1.22
    ました
    -1.21
     waż
    -1.17
    POSITIVE LOGITS
    ,
    1.56
     reager
    1.35
     tarjo
    1.30
    advert
    1.27
     SEÑ
    1.26
     aján
    1.25
     COMERC
    1.23
     rusty
    1.23
     megjelen
    1.22
     tatou
    1.22
    Activations Density 0.006%

    No Known Activations