© 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. 38598
    Prev
    Next
    INDEX
    Explanations

    desire and want to

    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
     our
    -1.86
     as
    -1.52
     all
    -1.45
    openhague
    -1.35
     other
    -1.34
     atriz
    -1.34
     several
    -1.30
      
    -1.30
     recently
    -1.30
     completely
    -1.27
    POSITIVE LOGITS
     régal
    1.40
    ーーーー
    1.40
    eve
    1.34
    垕
    1.31
    igkeit
    1.30
    鼉
    1.30
    を探す
    1.27
    ＊＊
    1.27
     öde
    1.27
    ーー
    1.26
    Activations Density 0.038%

    No Known Activations