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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103571
    Prev
    Next
    INDEX
    Explanations

    coordinates and dimensions

    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
     jednym
    -1.09
    rofoam
    -1.01
     escritores
    -0.99
     pieniądze
    -0.96
     Bevölkerung
    -0.95
     espressione
    -0.94
     acontecimientos
    -0.94
     rispar
    -0.93
    ussy
    -0.92
    cún
    -0.91
    POSITIVE LOGITS
     marat
    1.06
     pirata
    1.03
     antik
    1.00
     kapas
    0.93
     talle
    0.90
     africain
    0.90
     Profesional
    0.88
     miras
    0.88
     Elé
    0.86
     adil
    0.85
    Activations Density 0.023%

    No Known Activations