© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 47747
    Prev
    Next
    INDEX
    Explanations

    using System.Collections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Technische
    0.43
     Kirchner
    0.42
    ти
    0.39
     Vic
    0.39
    Technische
    0.39
    Ві
    0.39
     апо
    0.38
    Ѳ
    0.38
     También
    0.37
     formando
    0.37
    POSITIVE LOGITS
     interactive
    0.46
    interactive
    0.42
    Interactive
    0.42
    forder
    0.40
    فاق
    0.39
     المرا
    0.39
    وقف
    0.38
     tween
    0.38
    reng
    0.38
    
    0.37
    Activations Density 0.001%

    No Known Activations