© 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. 34-GEMMASCOPE-RES-131K
    7. 272
    Prev
    Next
    INDEX
    Explanations

    dma or estimation or preparation

    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_34/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
     Database
    -0.82
     XII
    -0.78
    Şi
    -0.76
     код
    -0.75
     Eing
    -0.74
    oleic
    -0.73
     Tamb
    -0.71
    GPIO
    -0.71
     Essex
    -0.70
     doce
    -0.70
    POSITIVE LOGITS
     transfer
    1.12
    transfer
    1.03
     transfers
    1.00
     Transfer
    0.97
     TRANSFER
    0.93
     transferring
    0.93
    Transfer
    0.93
     transferir
    0.86
     Transfers
    0.86
     transferencia
    0.85
    Activations Density 0.014%

    No Known Activations