© 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. 118782
    Prev
    Next
    INDEX
    Explanations

    analytical solutions and expressions

    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
    ೢ
    -1.56
     EconPapers
    -1.52
     utilisé
    -1.49
    ୩
    -1.46
    荭
    -1.41
    跸
    -1.39
    ={()
    -1.34
     boister
    -1.31
    мулятор
    -1.31
     adorned
    -1.31
    POSITIVE LOGITS
     because
    1.60
     and
    1.56
     February
    1.48
    Without
    1.40
     meille
    1.40
    ↵↵
    1.38
    Despite
    1.34
     includes
    1.29
     undoubtedly
    1.27
     plastico
    1.27
    Activations Density 0.052%

    No Known Activations