© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66190
    Prev
    Next
    INDEX
    Explanations

    programming language imports and declarations

    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
     Sitio
    -1.00
     galite
    -0.96
    Livraison
    -0.95
     castro
    -0.92
     either
    -0.91
     before
    -0.91
    Leistungs
    -0.90
     pollici
    -0.89
    romeda
    -0.88
    ecause
    -0.87
    POSITIVE LOGITS
    めっちゃ
    0.94
     entwickeln
    0.92
     победи
    0.89
    不时
    0.89
     Abenteuer
    0.88
     nuestros
    0.86
     développ
    0.86
    uala
    0.86
    чная
    0.85
     fuerte
    0.85
    Activations Density 0.003%

    No Known Activations