© 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. 127561
    Prev
    Next
    INDEX
    Explanations

    hurricanes and strong winds

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     نیز
    -1.40
     cũng
    -1.36
    Ꮺ
    -1.32
    𓆜
    -1.28
    👍👍
    -1.26
    谙
    -1.25
    äldrar
    -1.23
    “……
    -1.23
    vivencia
    -1.23
     galinha
    -1.22
    POSITIVE LOGITS
     cierra
    1.34
    一旁的
    1.27
     to
    1.27
     yesterday
    1.26
     its
    1.22
     verhindern
    1.20
    我好
    1.20
    給你
    1.18
    Sade
    1.17
     llegan
    1.16
    Activations Density 0.056%

    No Known Activations