© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 24836
    Prev
    Next
    INDEX
    Explanations

    who or whom

    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
     itself
    0.50
    Where
    0.44
    where
    0.44
    自体
    0.43
    த்திலேயே
    0.42
    maa
    0.41
    WHERE
    0.40
    s
    0.40
    ){}
    0.40
    与其他
    0.39
    POSITIVE LOGITS
     whom
    0.81
    whom
    0.71
     ktorí
    0.65
     którzy
    0.64
     who
    0.60
     kteří
    0.58
     cuyas
    0.53
     wheelchairs
    0.51
     Whom
    0.50
     whos
    0.50
    Activations Density 0.009%

    No Known Activations