© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7440
    Prev
    Next
    INDEX
    Explanations

    Abe eked, Atlético created, baby move

    np_acts-logits-general · gemini-2.5-flash-lite

    python regex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    是中国
    0.38
     হলেন
    0.37
    能在
    0.36
     Isn
    0.36
    uders
    0.35
    rogens
    0.34
    )['
    0.34
    在美国
    0.34
    是由
    0.34
    <unused2020>
    0.34
    POSITIVE LOGITS
    ฯ
    0.59
    광역시
    0.44
    대학교
    0.41
    日报
    0.40
     mellitus
    0.40
     الكريم
    0.40
     الرحمن
    0.39
     thaliana
    0.39
    الد
    0.39
    globals
    0.39
    Activations Density 0.072%

    No Known Activations