© 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. 77084
    Prev
    Next
    INDEX
    Explanations

    And lo

    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
    谑
    0.51
     expliquer
    0.50
    उंस
    0.46
     ยก
    0.46
    鐪
    0.46
     soort
    0.46
     বুঝি
    0.46
    视角
    0.45
     igre
    0.45
    멋
    0.45
    POSITIVE LOGITS
    begin
    0.47
     البلاد
    0.46
     July
    0.43
     signaling
    0.43
     university
    0.42
     Bản
    0.42
     leukocyte
    0.42
     ಜಿಲ್ಲ
    0.42
    。
    0.41
     blueberry
    0.41
    Activations Density 0.013%

    No Known Activations