© 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. 31-GEMMASCOPE-2-RES-65K
    7. 62009
    Prev
    Next
    INDEX
    Explanations

    explaining the following diagnosis or step

    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
    ровку
    0.45
    མ
    0.43
     Мы
    0.42
    뜹
    0.42
     ربعه
    0.41
    芢
    0.40
    ப்பையும்
    0.40
     обознача
    0.40
    ˄
    0.40
     происхождения
    0.39
    POSITIVE LOGITS
     soir
    0.41
     behov
    0.40
     neden
    0.38
     gio
    0.37
     actuellement
    0.37
    otransferase
    0.36
     her
    0.36
    ورية
    0.36
    cen
    0.35
     installing
    0.35
    Activations Density 0.024%

    No Known Activations