© 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-TRANSCODER-262K
    7. 54541
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by actions or possessions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    写真を
    0.36
    гази
    0.36
    स्टोन
    0.35
     juxtap
    0.34
     архів
    0.33
    逑
    0.33
    Checkpoint
    0.33
    >−</
    0.32
    Changing
    0.32
    するという
    0.32
    POSITIVE LOGITS
    ряд
    0.41
     CTC
    0.36
    ('',
    0.36
     jogs
    0.35
     জর
    0.35
    鬓
    0.35
    vene
    0.34
    fah
    0.34
    行
    0.34
     행
    0.34
    Activations Density 0.007%

    No Known Activations