© 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
    5. 16-GEMMASCOPE-2-RES-16K
    7. 776
    Prev
    Next
    INDEX
    Explanations

    possessive markers

    np_acts-logits-general · gemini-2.5-flash-lite

    prepositional phrase indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     a
    0.61
    ו
    0.60
    ów
    0.57
    erson
    0.56
    was
    0.54
    ids
    0.54
    art
    0.53
    V
    0.52
     was
    0.51
    verts
    0.51
    POSITIVE LOGITS
     in
    0.77
    ين
    0.68
    daki
    0.52
     인해
    0.52
    ని
    0.50
    larından
    0.50
    ల
    0.49
    larını
    0.49
    ྛ
    0.48
     في
    0.48
    Activations Density 2.344%

    No Known Activations