© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 108639
    Prev
    Next
    INDEX
    Explanations

    peaceful seashore or society

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

    heat loss, radiation, plague, baby

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     встре
    0.52
     officielles
    0.49
    راط
    0.48
    ње
    0.46
     рим
    0.46
     możli
    0.45
    有意
    0.45
    етесь
    0.44
    抖
    0.43
     سره
    0.43
    POSITIVE LOGITS
     peaceful
    0.54
     PATH
    0.53
     campsite
    0.52
    oggetto
    0.50
    oc
    0.50
     Peaceful
    0.50
     seashore
    0.49
     communal
    0.49
     society
    0.48
     riveting
    0.48
    Activations Density 0.000%

    No Known Activations