© 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. 40-GEMMASCOPE-2-RES-262K
    7. 224338
    Prev
    Next
    INDEX
    Explanations

    numbers, currency, cities

    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_40_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
    ﯾ
    0.38
    一颗
    0.37
    Geb
    0.37
     छत्तीसगढ़
    0.37
     Blackstone
    0.36
    Leng
    0.36
    堵
    0.36
     Hong
    0.36
     مل
    0.35
    جهات
    0.35
    POSITIVE LOGITS
    轍
    0.50
     Tc
    0.41
     Biraz
    0.41
     fermion
    0.40
     '\\
    0.40
    emitter
    0.39
     Src
    0.39
     biraz
    0.39
     پڑھی
    0.39
     Pentium
    0.38
    Activations Density 0.002%

    No Known Activations