© 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. 29974
    Prev
    Next
    INDEX
    Explanations

    technical descriptors

    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
    ات
    0.46
    ن
    0.40
    بر
    0.40
     ت
    0.39
    و
    0.39
     kom
    0.39
    ت
    0.39
     م
    0.38
    م
    0.38
    ي
    0.38
    POSITIVE LOGITS
    ᱗
    0.42
    原子力
    0.39
     最后
    0.39
     ойнойт
    0.38
     ଜ
    0.38
     কৰ
    0.38
     安全
    0.37
     ['(?
    0.37
     LOCCTR
    0.37
     实现
    0.37
    Activations Density 0.356%

    No Known Activations