© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11421
    Prev
    Next
    INDEX
    Explanations

    will support, We won, Self-magnetized, Clarence E

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     दौरान
    -1.13
    为什么
    -1.07
     žem
    -1.01
    前
    -0.99
    ftagPool
    -0.98
    అ
    -0.97
    图像
    -0.95
    ブログ
    -0.95
    zepam
    -0.94
    قبل
    -0.94
    POSITIVE LOGITS
    ylvan
    1.10
     zwei
    1.07
    むしろ
    1.05
    運輸
    1.03
     šte
    1.03
     tomto
    1.01
     Manusia
    1.01
    竟然是
    1.00
    Кита
    0.99
     doubly
    0.98
    Activations Density 0.000%

    No Known Activations