© 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. 12246
    Prev
    Next
    INDEX
    Explanations

    lists discussing sports leagues and teams

    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
     bénévol
    -1.34
    存于
    -1.33
    🗿
    -1.30
    ︱
    -1.29
    极为
    -1.27
    NÉ
    -1.27
    痪
    -1.26
    🦽
    -1.25
    BESCHREIBUNG
    -1.23
    During
    -1.23
    POSITIVE LOGITS
     who
    1.79
     zrobić
    1.45
    を変える
    1.33
    Referenties
    1.30
    5
    1.26
     prospet
    1.26
     then
    1.26
     sekund
    1.25
     importância
    1.24
    X
    1.24
    Activations Density 0.048%

    No Known Activations