© 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. 10-GEMMASCOPE-RES-131K
    7. 21030
    Prev
    Next
    INDEX
    Explanations

    Xsan, Kumbe, bedup, Q:

    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
     artesanía
    -1.65
     gastronomía
    -1.64
     estampado
    -1.45
     esquí
    -1.41
     soportes
    -1.38
    /*/
    -1.37
     fijn
    -1.35
    ILAR
    -1.29
     отды
    -1.28
     decorativo
    -1.27
    POSITIVE LOGITS
    Instead
    1.89
    Those
    1.80
    Surprisingly
    1.64
    Unfortunately
    1.55
    ícias
    1.55
    Another
    1.54
     Instead
    1.53
    Regardless
    1.49
    Although
    1.48
     Now
    1.47
    Activations Density 0.004%

    No Known Activations