© 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. 220147
    Prev
    Next
    INDEX
    Explanations

    recognizing contentment and discounts

    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
    チック
    0.43
     voisin
    0.41
     Shipbuilding
    0.41
    attaa
    0.40
     twine
    0.39
     MSU
    0.39
    aneity
    0.39
    ROP
    0.38
    抛
    0.38
     antik
    0.38
    POSITIVE LOGITS
     corrientes
    0.36
     regulación
    0.35
     DISCOUNT
    0.35
     rápidos
    0.35
     discount
    0.34
     quién
    0.34
    rtList
    0.33
     जिनको
    0.33
     Discount
    0.33
    bindingFields
    0.33
    Activations Density 0.000%

    No Known Activations