© 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. 31-GEMMASCOPE-2-RES-262K
    7. 107972
    Prev
    Next
    INDEX
    Explanations

    words following specific nouns

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

    writing text

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Logic
    0.49
    -
    0.46
    ायला
    0.46
    .
    0.46
     janvier
    0.45
     fireball
    0.45
    January
    0.44
    alsa
    0.43
    '
    0.43
     जैसी
    0.43
    POSITIVE LOGITS
     DEA
    0.50
     rewriting
    0.49
     ductility
    0.49
    ம்பு
    0.49
     кін
    0.48
     REQUIRED
    0.48
     UNIV
    0.48
    тинен
    0.47
     AGRE
    0.47
     ADJUST
    0.47
    Activations Density 0.004%

    No Known Activations