© 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. 10-GEMMASCOPE-RES-131K
    7. 13059
    Prev
    Next
    INDEX
    Explanations

    critical behavior and universality

    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_10/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
     which
    -1.72
    逦
    -1.50
    </h3>
    -1.43
    
    -1.43
     aproximativ
    -1.37
    茀
    -1.35
    協會
    -1.33
    anas
    -1.29
    lankton
    -1.29
     about
    -1.27
    POSITIVE LOGITS
    ньому
    1.51
    >−</
    1.25
    越来越
    1.23
     harap
    1.23
     весен
    1.20
     komik
    1.19
     Israël
    1.18
     should
    1.18
    urun
    1.16
     Karakter
    1.16
    Activations Density 0.058%

    No Known Activations