© 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. 119778
    Prev
    Next
    INDEX
    Explanations

    names like Louise and Rosen

    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
    鑁
    -2.53
    鸸
    -2.31
    戗
    -2.23
    '
    -2.23
     accedi
    -2.20
    猡
    -2.20
     ifølge
    -2.17
    лении
    -2.17
     stessa
    -2.14
     kteří
    -2.14
    POSITIVE LOGITS
    i
    2.95
    0
    2.78
    7
    2.72
    v
    2.70
     для
    2.69
    He
    2.69
    1
    2.67
    3
    2.66
    6
    2.64
     и
    2.59
    Activations Density 0.004%

    No Known Activations