© 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. 41378
    Prev
    Next
    INDEX
    Explanations

    technical and foreign terms

    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
     nawet
    -1.60
     even
    -1.59
    even
    -1.50
    According
    -1.45
     already
    -1.42
     навіть
    -1.41
    même
    -1.40
     fonctionne
    -1.34
     circulación
    -1.33
     incluso
    -1.31
    POSITIVE LOGITS
     from
    1.84
     has
    1.72
     These
    1.48
    спу
    1.44
    ICIAS
    1.39
     hermano
    1.33
    ibilità
    1.33
    寄生
    1.31
    FundMe
    1.30
    fromUtf
    1.29
    Activations Density 0.231%

    No Known Activations