© 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. 65982
    Prev
    Next
    INDEX
    Explanations

    data partitioning

    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
     contextual
    -0.83
     gastar
    -0.82
     lâu
    -0.79
     calories
    -0.77
    méno
    -0.75
    ardio
    -0.75
    khan
    -0.73
     πισ
    -0.72
     powinna
    -0.71
    iburg
    -0.71
    POSITIVE LOGITS
     hash
    1.13
    hash
    1.05
    Hash
    1.03
     Hash
    1.02
     Range
    1.02
     evenly
    1.00
     range
    0.98
     partitioning
    0.94
     partition
    0.94
     RANGE
    0.91
    Activations Density 0.034%

    No Known Activations