© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 2967
    Prev
    Next
    INDEX
    Explanations

    explains why something is important

    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
    яти
    0.45
     Hing
    0.40
     Earrings
    0.40
     Yat
    0.39
     outliers
    0.37
    Kayak
    0.37
    ubers
    0.36
    χ
    0.36
     нека
    0.35
    χε
    0.34
    POSITIVE LOGITS
     why
    0.87
     mengapa
    0.83
    為什麼
    0.80
    why
    0.76
    为什么
    0.73
     waarom
    0.68
     kenapa
    0.68
     почему
    0.61
     reflected
    0.61
    왜
    0.60
    Activations Density 0.235%

    No Known Activations