© 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. 70609
    Prev
    Next
    INDEX
    Explanations

    company or government 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
     навіть
    -1.84
    Pengertian
    -1.61
    Either
    -1.55
    スコット
    -1.54
    Sejarah
    -1.53
     дуже
    -1.52
    Seems
    -1.50
     offrant
    -1.48
    ترت
    -1.45
    either
    -1.42
    POSITIVE LOGITS
     will
    2.34
    </h2>
    1.74
     also
    1.63
     expected
    1.62
    inafter
    1.49
     must
    1.46
    amment
    1.46
    ga
    1.45
    |}{
    1.42
     belangrij
    1.40
    Activations Density 0.108%

    No Known Activations