© 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. 131008
    Prev
    Next
    INDEX
    Explanations

    HTML PUBLIC identifier

    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
     its
    -1.70
    るのは
    -1.70
     speziellen
    -1.68
     '
    -1.58
     получил
    -1.57
    总裁
    -1.56
    民众
    -1.55
     apoya
    -1.48
     genutzt
    -1.46
     envía
    -1.45
    POSITIVE LOGITS
     of
    1.73
     aimer
    1.72
     dorp
    1.56
    étiques
    1.53
     they
    1.53
     作り方
    1.52
    ✓
    1.51
    )=\
    1.50
     nimi
    1.45
     idyl
    1.45
    Activations Density 0.010%

    No Known Activations