© 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. 68417
    Prev
    Next
    INDEX
    Explanations

    deterioration, damage, or wear

    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
     dessutom
    -1.38
     hábiles
    -1.34
     alltså
    -1.34
     fortfarande
    -1.31
     információ
    -1.28
     säkert
    -1.23
     változ
    -1.22
    eapples
    -1.21
     :
    -1.20
     inútil
    -1.20
    POSITIVE LOGITS
     when
    1.73
     We
    1.60
     cuando
    1.49
    rdoba
    1.46
     predecess
    1.42
    cuando
    1.41
    jabat
    1.30
     our
    1.25
     sobald
    1.24
    terus
    1.20
    Activations Density 0.093%

    No Known Activations