© 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. 766
    Prev
    Next
    INDEX
    Explanations

    variable assignment or definition

    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
    แมนเชสเตอร์ซิตี
    0.39
    🖥
    0.38
     फ्रॉम
    0.38
     ബാറ്ററി
    0.38
    sels
    0.38
     ఇతర
    0.37
    ⵜ
    0.37
    ွင့်
    0.36
     መጠቀም
    0.36
    ใช้
    0.36
    POSITIVE LOGITS
    টিতে
    0.36
     இடை
    0.35
     Seventy
    0.34
     panel
    0.34
     ABSTRACT
    0.33
     incomplete
    0.33
     "
    0.32
     যাবে
    0.32
    begin
    0.32
     value
    0.32
    Activations Density 0.003%

    No Known Activations