© 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. 22-GEMMASCOPE-RES-131K
    7. 127655
    Prev
    Next
    INDEX
    Explanations

    mountain heights or questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    İş
    -1.29
    QUÉ
    -1.24
    场比赛
    -1.23
    İyi
    -1.17
    alties
    -1.15
    Escolha
    -1.15
    Saiba
    -1.14
    𝜔
    -1.13
     merve
    -1.13
    ึกษา
    -1.12
    POSITIVE LOGITS
    fycat
    1.19
    อร่อย
    1.15
    erweise
    1.14
    alami
    1.07
     ویتامین
    1.01
     of
    1.00
    etap
    0.98
     włosów
    0.97
     има
    0.96
     primeiras
    0.96
    Activations Density 0.001%

    No Known Activations