© 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. 3904
    Prev
    Next
    INDEX
    Explanations

    reason or purpose

    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
    OUTUBE
    -1.44
    錮
    -1.37
     обладает
    -1.36
     excels
    -1.35
     handleMessage
    -1.29
    </i>
    -1.27
    梣
    -1.27
    pecabe
    -1.26
     rises
    -1.23
     arrives
    -1.23
    POSITIVE LOGITS
     Therefore
    1.59
     gän
    1.52
     And
    1.49
     We
    1.47
    或者
    1.46
    some
    1.46
    example
    1.45
     Traducción
    1.41
    したり
    1.40
    pperware
    1.40
    Activations Density 0.018%

    No Known Activations