© 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. 102707
    Prev
    Next
    INDEX
    Explanations

    amountswater

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

    adverbs modifying descriptive adjectives/nouns

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ajj
    0.47
    📏
    0.46
    แพทย์
    0.45
    ເພດ
    0.45
     গমন
    0.44
     advisable
    0.44
    ຕ້ອງ
    0.44
     please
    0.43
    ພວກເຮ
    0.43
    ндан
    0.43
    POSITIVE LOGITS
     მს
    0.45
    า
    0.44
     dto
    0.44
    في
    0.43
    Hin
    0.42
    Kunst
    0.42
    contribution
    0.42
    ANCIAL
    0.41
    "]},{"
    0.41
    Bunch
    0.40
    Activations Density 0.000%

    No Known Activations