© 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-262K
    7. 40892
    Prev
    Next
    INDEX
    Explanations

    Alibaba, Shanghai, Hangzhou, China

    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_262k_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
     Lockhart
    0.48
     Horticulture
    0.46
     Schm
    0.46
     Josiah
    0.45
    萂
    0.45
     Battles
    0.44
     Drexel
    0.44
    zers
    0.44
    綏
    0.43
    藠
    0.43
    POSITIVE LOGITS
     Alibaba
    0.63
    杭州
    0.58
    上海
    0.56
    Shanghai
    0.56
     Shanghai
    0.55
     Chinese
    0.52
     上海
    0.51
     Hangzhou
    0.51
     Alipay
    0.50
     चीन
    0.50
    Activations Density 0.009%

    No Known Activations