© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 63550
    Prev
    Next
    INDEX
    Explanations

    capital city, regal, convenient

    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
     comen
    0.42
     deacon
    0.39
     dama
    0.38
     deixe
    0.38
     desenvolv
    0.37
     desenvolver
    0.36
    闖
    0.36
    ้องกัน
    0.35
    ুমার
    0.35
    neutral
    0.35
    POSITIVE LOGITS
     обеспечивает
    0.42
    优势
    0.41
     તેવી
    0.40
     Spor
    0.39
     Ljubljana
    0.37
     subtropical
    0.36
     یخچال
    0.36
    ))^
    0.36
     রাজধানী
    0.36
     Illumina
    0.36
    Activations Density 0.007%

    No Known Activations