© 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. 31-GEMMASCOPE-2-RES-65K
    7. 56731
    Prev
    Next
    INDEX
    Explanations

    trick question widow

    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_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     muttered
    0.49
     conso
    0.45
     player
    0.45
     mumbled
    0.45
     serialized
    0.44
     সীমান্তবর্তী
    0.43
     hood
    0.43
    л
    0.43
     하나님
    0.42
    быз
    0.42
    POSITIVE LOGITS
    ر
    0.53
    اض
    0.44
    ાસ
    0.42
    宩
    0.42
     Ángeles
    0.41
    قافة
    0.41
    ാഗ
    0.40
    قق
    0.40
    ندن
    0.40
    ิท
    0.39
    Activations Density 0.015%

    No Known Activations