© 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. 20893
    Prev
    Next
    INDEX
    Explanations

    technical explanations

    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
     porque
    0.50
     prostitution
    0.47
     γιατί
    0.46
    ५
    0.46
     vì
    0.45
     perquè
    0.44
     क्योंकि
    0.42
     apont
    0.42
     pessoal
    0.42
     répét
    0.42
    POSITIVE LOGITS
    鹂
    0.44
    前提
    0.41
    她们
    0.39
     উচিৎ
    0.39
    锌
    0.39
     occurring
    0.37
     toekom
    0.37
    他们的
    0.36
    എം
    0.36
     ისინი
    0.36
    Activations Density 0.001%

    No Known Activations