© 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. 72162
    Prev
    Next
    INDEX
    Explanations

    geographical or technical 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
    кло
    -0.99
     pediatric
    -0.99
     spowod
    -0.98
    達は
    -0.94
        
    -0.92
     пру
    -0.90
     zakup
    -0.88
     statysty
    -0.88
    还在
    -0.87
     Metern
    -0.87
    POSITIVE LOGITS
     there
    0.87
     dizem
    0.85
     hydrat
    0.84
     kerap
    0.83
     Çünkü
    0.81
    født
    0.80
    ıda
    0.80
    ələ
    0.77
     ech
    0.77
    áv
    0.76
    Activations Density 0.515%

    No Known Activations