© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 5878
    Prev
    Next
    INDEX
    Explanations

    Korean and Japanese suffixes

    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
    の
    0.47
    を
    0.46
    的
    0.44
     be
    0.43
    =
    0.42
    に
    0.42
     yang
    0.40
     arouse
    0.38
    <0xE6>
    0.38
     then
    0.38
    POSITIVE LOGITS
    癤
    0.34
    flächen
    0.34
    이제
    0.34
    鸫
    0.33
    玧
    0.33
    藓
    0.32
     결국
    0.32
     መጠን
    0.31
     Інтэр
    0.31
    Manufacturing
    0.31
    Activations Density 0.002%

    No Known Activations