© 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. 40-GEMMASCOPE-2-RES-262K
    7. 99783
    Prev
    Next
    INDEX
    Explanations

    surname components

    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_40_width_262k_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
    锏
    0.42
    REIB
    0.40
    melting
    0.40
     Noether
    0.39
     Krist
    0.38
     Kreuz
    0.38
     ghe
    0.38
    kä
    0.37
    ہنی
    0.37
     Kf
    0.36
    POSITIVE LOGITS
     রহিয়াছে
    0.43
     Witherspoon
    0.42
     dx
    0.41
     భ
    0.40
    emore
    0.39
     Dawkins
    0.38
     dix
    0.38
     Salaam
    0.38
    asley
    0.38
     lewis
    0.38
    Activations Density 0.003%

    No Known Activations