© 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. 9582
    Prev
    Next
    INDEX
    Explanations

    D. followed by names

    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
     wszyst
    -1.40
    がこの
    -1.36
    なんか
    -1.34
    凩
    -1.34
     interesar
    -1.29
     حيث
    -1.27
    一切都
    -1.27
    ೢ
    -1.27
     gelangt
    -1.27
     certains
    -1.27
    POSITIVE LOGITS
     mereka
    1.55
     גם
    1.50
     човек
    1.38
     نیز
    1.37
     is
    1.30
    亙
    1.29
     because
    1.28
    ată
    1.26
     también
    1.24
    ”،
    1.24
    Activations Density 0.037%

    No Known Activations