© 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. 31-GEMMASCOPE-2-RES-65K
    7. 54060
    Prev
    Next
    INDEX
    Explanations

    normal, healthy, legitimate

    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
     Lâm
    0.42
     sélectionnez
    0.42
    庣
    0.37
     chọn
    0.37
    ⇨
    0.36
    Ү
    0.35
    取得
    0.35
     റോ
    0.35
     Lesley
    0.35
     Ро
    0.34
    POSITIVE LOGITS
    正常的
    0.80
     legitimately
    0.73
     harmless
    0.71
     legitimate
    0.70
     normal
    0.69
    正常
    0.69
    合理
    0.67
    合理的
    0.67
     healthy
    0.62
     NORMAL
    0.61
    Activations Density 0.219%

    No Known Activations