© 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. 12779
    Prev
    Next
    INDEX
    Explanations

    engine cooling components

    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
    踵
    -1.46
     It
    -1.41
     will
    -1.34
     широкий
    -1.32
    tól
    -1.30
    しつつ
    -1.28
     greets
    -1.27
     polie
    -1.27
     has
    -1.26
     about
    -1.26
    POSITIVE LOGITS
    ALLEL
    1.32
     moi
    1.29
     fantastic
    1.22
    鴬
    1.20
    场合
    1.16
    レンタ
    1.14
     "");
    1.14
     diseñados
    1.13
     görüntüleri
    1.13
    boxy
    1.13
    Activations Density 0.012%

    No Known Activations