© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 75149
    Prev
    Next
    INDEX
    Explanations

    football clubs and players

    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
     Permite
    -1.44
    -1.28
    它
    -1.23
     directement
    -1.20
    !
    -1.20
     追加
    -1.19
     новое
    -1.19
     daje
    -1.18
    płat
    -1.16
     позволяет
    -1.16
    POSITIVE LOGITS
     according
    1.64
    ícias
    1.39
    (!__
    1.25
     we
    1.25
     všechny
    1.23
    Hermoso
    1.21
     volgens
    1.20
    Endereco
    1.20
    ்க்க
    1.19
     izman
    1.19
    Activations Density 0.052%

    No Known Activations