© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67168
    Prev
    Next
    INDEX
    Explanations

    binary file reading and decoding

    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
    ↵↵
    -1.15
    ＇
    -1.04
    遞
    -1.01
     criação
    -0.98
    0
    -0.97
     igreja
    -0.96
    c
    -0.95
    new
    -0.95
    =
    -0.94
    包装
    -0.94
    POSITIVE LOGITS
    vantaged
    1.10
    を発表
    1.09
     ispir
    1.03
    üstet
    1.03
    правления
    1.02
    áme
    1.02
    quarelle
    1.02
     развитию
    1.00
     tayang
    1.00
    瞜
    0.98
    Activations Density 0.004%

    No Known Activations