© 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. 20314
    Prev
    Next
    INDEX
    Explanations

    this invention

    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
     of
    -1.91
    to
    -1.68
     last
    -1.62
    Of
    -1.62
     precedenti
    -1.57
     previous
    -1.55
     our
    -1.54
     for
    -1.45
     Both
    -1.45
    Both
    -1.45
    POSITIVE LOGITS
     maravill
    1.88
     espejos
    1.70
    .
    1.62
     atractivos
    1.58
    neden
    1.55
    ăți
    1.52
     cristales
    1.52
     agujeros
    1.49
     bocetos
    1.47
     hermosos
    1.46
    Activations Density 0.004%

    No Known Activations