© 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. 9231
    Prev
    Next
    INDEX
    Explanations

    Understanding the Goal

    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
     მათ
    0.38
    <unused1013>
    0.38
     також
    0.37
    についても
    0.37
     ايضا
    0.37
     также
    0.35
    ה
    0.35
    <unused1731>
    0.35
    <unused406>
    0.35
    ༩
    0.35
    POSITIVE LOGITS
     majority
    0.36
     recommended
    0.36
     Majority
    0.36
    你需要
    0.35
     You
    0.34
     Depending
    0.34
     A
    0.34
     K
    0.33
    ,
    0.32
     The
    0.32
    Activations Density 0.722%

    No Known Activations