© 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. 10-GEMMASCOPE-RES-131K
    7. 20959
    Prev
    Next
    INDEX
    Explanations

    introducing abbreviation or term

    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
    或者
    -3.19
     และ
    -2.97
     или
    -2.95
     یا
    -2.88
     ausein
    -2.83
     \&
    -2.78
     atau
    -2.64
    或
    -2.56
     וה
    -2.47
    ቕ
    -2.39
    POSITIVE LOGITS
    </h3>
    2.66
    縯
    2.59
     achieving
    2.56
     That
    2.45
    e
    2.42
     characterize
    2.36
     outros
    2.34
    灩
    2.25
    偌
    2.25
     stating
    2.25
    Activations Density 0.017%

    No Known Activations