© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34259
    Prev
    Next
    INDEX
    Explanations

    comparisons and code logic

    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
    Not in Any Lists

    No Comments

    Negative Logits
     heilig
    -1.07
     verle
    -1.07
     wandel
    -0.98
    ltä
    -0.98
     wacht
    -0.95
    
    -0.94
    [])
    -0.93
    datable
    -0.93
    емой
    -0.90
    _{{\
    -0.89
    POSITIVE LOGITS
     also
    1.05
     شامل
    0.94
     даже
    0.91
     Dacă
    0.90
     even
    0.90
    ığımız
    0.89
     Clusters
    0.89
     Acest
    0.88
     because
    0.88
    Cuad
    0.87
    Activations Density 0.009%

    No Known Activations