© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 64407
    Prev
    Next
    INDEX
    Explanations

    sailing and racing

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

    The neuron fires on maritime/sailing language—especially boat names, race events, sailing actions, distances, speeds, and related nautical terminology.

    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
     your
    -1.60
    我对
    -1.51
    子供が
    -1.34
    expiresIn
    -1.33
     подрост
    -1.28
    Учитель
    -1.26
    ffiti
    -1.21
    螈
    -1.20
    item
    -1.20
    chymal
    -1.19
    POSITIVE LOGITS
     campeonato
    1.41
     auroit
    1.36
     météo
    1.35
     reconnaît
    1.35
    อร่อย
    1.34
     complicada
    1.30
    颚
    1.27
     tfsi
    1.25
     étoit
    1.25
    ₐ
    1.23
    Activations Density 0.015%

    No Known Activations