© 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. 34-GEMMASCOPE-RES-131K
    7. 30925
    Prev
    Next
    INDEX
    Explanations

    try to max

    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_34/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
    хать
    -0.99
     calificaciones
    -0.96
     aislamiento
    -0.93
    urlpatterns
    -0.91
     localizar
    -0.91
     jonge
    -0.88
     reciclaje
    -0.87
    aknya
    -0.87
     descubrimiento
    -0.87
     eenvou
    -0.86
    POSITIVE LOGITS
     max
    1.30
     use
    1.05
    max
    1.03
     only
    0.98
     spam
    0.96
     get
    0.83
     play
    0.81
     equip
    0.81
     plays
    0.81
     роки
    0.81
    Activations Density 0.018%

    No Known Activations