© 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. 54801
    Prev
    Next
    INDEX
    Explanations

    explanation using words from different languages

    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
     NGOs
    0.48
     SCHEMA
    0.48
     (=
    0.46
     morphogenesis
    0.45
     setempat
    0.45
    ≒
    0.45
     nonprofits
    0.45
    ગવાન
    0.44
    😪
    0.44
     pathogenesis
    0.43
    POSITIVE LOGITS
     içerisinde
    0.57
     sizlere
    0.55
     நீங்கள்
    0.53
     العديد
    0.53
     различных
    0.52
     ඔබට
    0.52
     você
    0.52
     вам
    0.52
    小编
    0.50
     całkow
    0.49
    Activations Density 0.006%

    No Known Activations