© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 13138
    Prev
    Next
    INDEX
    Explanations

    beyond the superficial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    प्ट
    0.38
     रियल
    0.37
     अफवाह
    0.36
     reales
    0.36
     реаль
    0.36
     pomer
    0.36
    ₕ
    0.36
     pril
    0.35
    ∞
    0.35
     dynam
    0.35
    POSITIVE LOGITS
     merely
    0.73
     rote
    0.61
     brute
    0.61
     mere
    0.59
     reactive
    0.57
     Reactive
    0.57
     superficial
    0.56
    Reactive
    0.55
     단순히
    0.55
     Descriptive
    0.53
    Activations Density 0.083%

    No Known Activations