© 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. 40390
    Prev
    Next
    INDEX
    Explanations

    code comments and separators

    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
    ：「
    0.45
    床
    0.44
     }=\
    0.42
    地区
    0.41
    দৃষ্টি
    0.40
    以下
    0.39
     )।
    0.39
    ルの
    0.38
    levision
    0.38
     તેણીએ
    0.38
    POSITIVE LOGITS
     Gosudarstvennyj
    0.45
    Env
    0.43
     পয়
    0.42
    拽
    0.38
    Aut
    0.38
     аў
    0.37
     aut
    0.37
     هناخد
    0.37
     Estatal
    0.37
     құ
    0.36
    Activations Density 0.010%

    No Known Activations