© 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. 3701
    Prev
    Next
    INDEX
    Explanations

    css and android code

    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
     Otros
    -1.48
    RICAL
    -1.44
    そんな
    -1.40
    IANT
    -1.35
    こんな
    -1.34
    ви
    -1.31
     commencé
    -1.31
    Daha
    -1.30
     fantastisk
    -1.28
     таком
    -1.27
    POSITIVE LOGITS
     it
    1.83
     on
    1.70
    。“
    1.55
     some
    1.50
    、“
    1.45
     coming
    1.32
    。　　
    1.28
     will
    1.26
     does
    1.25
     making
    1.25
    Activations Density 0.062%

    No Known Activations