© 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. 235350
    Prev
    Next
    INDEX
    Explanations

    technical terms and international words

    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
     Hazards
    0.47
     Bless
    0.46
    弊
    0.43
    etzes
    0.42
    からです
    0.42
    部落
    0.41
    曛
    0.41
    irts
    0.40
    сть
    0.40
     तथ
    0.40
    POSITIVE LOGITS
    မာ
    0.50
     infringe
    0.49
     აღმასრულ
    0.47
     hermoso
    0.46
     magnifique
    0.46
     extensible
    0.46
    ྰ
    0.46
     lactate
    0.46
     marché
    0.46
     الأطفال
    0.45
    Activations Density 0.000%

    No Known Activations