© 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-16K
    7. 555
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     aby
    0.39
     כדי
    0.36
    RationalValue
    0.35
     تاکہ
    0.35
     upang
    0.34
     flamb
    0.33
    それを
    0.33
     savent
    0.32
     αρκε
    0.32
    ﺒ
    0.32
    POSITIVE LOGITS
     from
    0.60
     of
    0.58
     across
    0.55
     của
    0.54
     on
    0.53
     between
    0.50
     của
    0.48
     in
    0.46
     från
    0.44
     within
    0.44
    Activations Density 2.734%

    No Known Activations