© 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. 27049
    Prev
    Next
    INDEX
    Explanations

    listing items and 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
    פ
    0.36
    思想
    0.34
    ས
    0.34
    ்
    0.33
    式
    0.33
    hemian
    0.32
     jellyfish
    0.32
    芬
    0.32
    ந்திய
    0.32
    回头
    0.32
    POSITIVE LOGITS
     etc
    0.48
     etcétera
    0.48
     కూడా
    0.46
    或其他
    0.46
     itp
    0.45
     appunto
    0.45
     itd
    0.44
     أيضا
    0.44
     usw
    0.43
     Indeed
    0.43
    Activations Density 0.211%

    No Known Activations