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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 54365
    Prev
    Next
    INDEX
    Explanations

    ports, protocols, 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_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
    ز
    0.45
    galaxys
    0.40
    microwave
    0.38
    㢳
    0.38
     სახ
    0.37
    _:
    0.37
     underlines
    0.37
    supers
    0.36
     প্রজাতন্ত্র
    0.36
    preserve
    0.36
    POSITIVE LOGITS
     toil
    0.44
     быстро
    0.43
     rbuf
    0.42
    撸
    0.42
     trayectoria
    0.41
    dbh
    0.40
     mno
    0.40
     clasific
    0.40
     godinu
    0.39
    ༡
    0.39
    Activations Density 0.002%

    No Known Activations