© 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. 5756
    Prev
    Next
    INDEX
    Explanations

    answer

    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
     Дмитри
    0.42
     یہودیوں
    0.41
     Kud
    0.38
     Timurtaş
    0.37
     sofr
    0.37
     dukkh
    0.37
    bedkar
    0.37
    important
    0.36
     ڈپ
    0.36
    :...
    0.36
    POSITIVE LOGITS
    ．
    0.36
     devices
    0.34
     grow
    0.34
     oub
    0.34
    aini
    0.34
    راع
    0.34
    及び
    0.34
    োম
    0.34
     গ্রহণ
    0.33
     persuasion
    0.33
    Activations Density 0.002%

    No Known Activations