© 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. 15611
    Prev
    Next
    INDEX
    Explanations

    opening greetings

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

    This neuron detects informal greeting openings (e.g. “Hi there,” “Hey there,” “Hello there,” etc.) at the start of posts.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    </h4>
    -1.66
    観て
    -1.63
     главный
    -1.58
     atentos
    -1.55
     ผม
    -1.50
     Besonder
    -1.47
     két
    -1.44
    出た
    -1.42
     però
    -1.40
    又は
    -1.40
    POSITIVE LOGITS
    There
    2.06
    they
    2.03
     there
    1.92
    there
    1.76
    Not
    1.68
    Although
    1.66
     они
    1.61
    各式
    1.60
    seeable
    1.59
     ikke
    1.59
    Activations Density 0.006%

    No Known Activations