© 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. 19865
    Prev
    Next
    INDEX
    Explanations

    Php url

    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
    喾
    -2.72
    arthed
    -2.69
     europe
    -2.61
    驽
    -2.55
    泚
    -2.50
    ⚣
    -2.47
    诳
    -2.44
    媗
    -2.44
    offers
    -2.44
    ным
    -2.44
    POSITIVE LOGITS
    t
    2.84
    卨
    2.45
     größer
    2.42
    ت
    2.31
    或者
    2.31
     einfacher
    2.23
    𓆜
    2.22
    因為
    2.19
     privada
    2.16
    据说
    2.16
    Activations Density 0.034%

    No Known Activations