© 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. 16684
    Prev
    Next
    INDEX
    Explanations

    command separators or section titles

    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
    ultor
    -1.08
     konflikt
    -1.05
     dalších
    -0.99
     Gemüse
    -0.96
     Gemü
    -0.96
     Vorteile
    -0.93
     konflik
    -0.92
     Früchte
    -0.91
     Erkenntnisse
    -0.90
     Erzä
    -0.88
    POSITIVE LOGITS
     esso
    0.92
    銳
    0.91
    usa
    0.91
    ilesh
    0.89
     corris
    0.89
    쫓
    0.88
    fda
    0.87
     Ruck
    0.87
     雲
    0.86
     Rosso
    0.85
    Activations Density 0.000%

    No Known Activations