© 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. 176969
    Prev
    Next
    INDEX
    Explanations

    Thailand cosmetic surgery

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

    environment, System, Data, Graphics

    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
    人和
    0.46
    ாக
    0.45
    恍
    0.44
    孀
    0.43
    呿
    0.43
    ات
    0.43
    ες
    0.43
    淪
    0.43
     বয়
    0.42
    囿
    0.42
    POSITIVE LOGITS
     système
    0.50
     cupcakes
    0.49
     délais
    0.49
     déchets
    0.49
     activité
    0.48
     liquides
    0.48
     citoyens
    0.47
     impuestos
    0.45
     chargés
    0.45
     munitions
    0.45
    Activations Density 0.001%

    No Known Activations