© 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-262K
    7. 33182
    Prev
    Next
    INDEX
    Explanations

    questions that engage

    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_262k_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
     application
    0.51
    ጨማሪ
    0.50
     Application
    0.47
     масштаб
    0.47
     Від
    0.47
    application
    0.46
     Ги
    0.46
    드
    0.46
     Ки
    0.46
     Д
    0.46
    POSITIVE LOGITS
     tiket
    0.42
    odisc
    0.40
     സെക്രട്ട
    0.39
     tiros
    0.39
     turun
    0.38
     dormir
    0.38
     harmonies
    0.38
     najbli
    0.38
     interrump
    0.38
     riforma
    0.38
    Activations Density 0.001%

    No Known Activations