© 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-16K
    7. 9770
    Prev
    Next
    INDEX
    Explanations

    csharp code examples

    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_16k_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
    glichen
    0.46
     Lang
    0.43
     Ven
    0.41
     School
    0.41
     Nagar
    0.39
     Verb
    0.39
     Dun
    0.39
    狀
    0.39
     Dunk
    0.38
     Verma
    0.38
    POSITIVE LOGITS
     funniest
    0.51
     specialises
    0.44
    ័រ
    0.44
     oscillate
    0.43
     enjoys
    0.43
     playable
    0.42
     craziness
    0.42
     સંપૂર્ણ
    0.42
    쥬
    0.42
     parody
    0.41
    Activations Density 0.021%

    No Known Activations