© 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. 15293
    Prev
    Next
    INDEX
    Explanations

    names and specific terms

    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
     dzięki
    -1.11
    före
    -1.05
    多谢
    -1.05
     Unterstützung
    -1.00
     Ask
    -1.00
     and
    -0.99
    Each
    -0.96
     بيها
    -0.92
    nyata
    -0.90
    Thanks
    -0.90
    POSITIVE LOGITS
     brosse
    1.21
     flamme
    1.02
     goutte
    0.99
     Seeder
    0.98
     stop
    0.98
     faune
    0.96
     Zaman
    0.95
     Putri
    0.94
     způso
    0.94
     Brot
    0.93
    Activations Density 0.002%

    No Known Activations