© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 114078
    Prev
    Next
    INDEX
    Explanations

    adsorbent, polymer, heifers, disease

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

    words ending in "bent" or "ent" that relate to adsorption, absorption, or other scientific processes.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    e
    -3.02
     разные
    -2.81
    am
    -2.52
    archiwizowane
    -2.45
    了一个
    -2.41
     them
    -2.39
    ”;
    -2.36
     работают
    -2.34
    aktiv
    -2.33
    呿
    -2.33
    POSITIVE LOGITS
    ſelf
    2.64
    뿡
    2.56
    猹
    2.50
    t
    2.44
    ꔛ
    2.41
    OUTUBE
    2.39
    ://"
    2.38
    뿍
    2.38
    ଢ
    2.36
    蒟
    2.33
    Activations Density 0.037%

    No Known Activations