© 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. 34-GEMMASCOPE-RES-131K
    7. 47091
    Prev
    Next
    INDEX
    Explanations

    Stream, invention, connectivity

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

    The neuron picks up on first‐person organizational or promotional announcements (e.g. “Our Team…is anxious to find…learn more…”)

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    いつでも
    -0.76
     kiedyś
    -0.75
     こちら
    -0.73
     zobaczyć
    -0.73
    向前
    -0.70
     geologist
    -0.70
     inflexible
    -0.70
    価値
    -0.70
     kemeja
    -0.69
    議会
    -0.68
    POSITIVE LOGITS
    CONNECT
    1.21
    Connect
    1.12
     Stream
    1.05
    Stream
    0.98
    connect
    0.98
     stream
    0.98
    ff
    0.93
     Connect
    0.93
     Spotify
    0.92
     algo
    0.91
    Activations Density 0.006%

    No Known Activations