© 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. 66118
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols

    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
    offers
    -1.57
     juzgar
    -1.49
    ଃ
    -1.48
     スーパー
    -1.46
    その他
    -1.46
     altre
    -1.45
    場合
    -1.44
    presents
    -1.42
     debería
    -1.41
     而
    -1.41
    POSITIVE LOGITS
     reizen
    1.34
     Careful
    1.32
    ítu
    1.30
    灬
    1.29
     Vorschlag
    1.27
    ၜ
    1.24
    忐
    1.23
     maximise
    1.22
     グッズ
    1.22
    ınızı
    1.21
    Activations Density 0.048%

    No Known Activations