© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 11728
    Prev
    Next
    INDEX
    Explanations

    authenticity and self-worth

    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
    loadNpm
    0.44
    テーション
    0.43
    男人
    0.43
     উৎপাদন
    0.43
     давайте
    0.42
     каждым
    0.42
    ⬮
    0.42
     ecmaVersion
    0.41
    מ
    0.41
     глю
    0.40
    POSITIVE LOGITS
     topics
    0.47
     viewers
    0.44
     topic
    0.41
     Wals
    0.40
     embezz
    0.40
     callers
    0.40
     companies
    0.39
     Market
    0.38
     Topics
    0.38
     proposer
    0.38
    Activations Density 0.027%

    No Known Activations