© 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. 16536
    Prev
    Next
    INDEX
    Explanations

    speaking before

    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
     also
    -1.43
     to
    -1.34
     (
    -1.21
     We
    -1.16
     That
    -1.13
     It
    -1.13
    ？　
    -1.11
     But
    -1.09
     for
    -1.05
     No
    -1.02
    POSITIVE LOGITS
     eerste
    1.32
     parlare
    1.30
     görüntüsü
    1.29
    zurück
    1.28
     аккура
    1.27
    förmig
    1.25
    Ressources
    1.23
    aktivi
    1.21
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.20
    Terug
    1.20
    Activations Density 0.005%

    No Known Activations