© 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. 61120
    Prev
    Next
    INDEX
    Explanations

    serialization formats

    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
    förderung
    -1.72
    ↵↵
    -1.58
    "..."
    -1.48
    꽤
    -1.45
    </b>
    -1.43
     \&
    -1.40
    AYA
    -1.34
    梆
    -1.34
     获取
    -1.30
     customize
    -1.30
    POSITIVE LOGITS
    だそうです
    1.47
    They
    1.38
    ociação
    1.32
    狨
    1.29
    çası
    1.27
    スーツ
    1.27
    れました
    1.23
     Schloß
    1.23
     لأنه
    1.21
     debemos
    1.20
    Activations Density 0.041%

    No Known Activations