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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70526
    Prev
    Next
    INDEX
    Explanations

    conduct

    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_10/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
    يل
    -2.47
    ized
    -2.45
    vantaged
    -2.36
    偌
    -2.17
     kekasih
    -2.06
    ed
    -2.05
     некоторые
    -2.02
     связано
    -2.02
     halted
    -1.99
     evidenced
    -1.97
    POSITIVE LOGITS
    ”，
    2.77
    ”),
    2.64
    ”)
    2.47
    
    2.41
    檍
    2.30
    ”).
    2.17
    ——”
    2.17
    》，
    2.14
    </em>
    2.13
     patrick
    2.13
    Activations Density 0.005%

    No Known Activations