© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 107422
    Prev
    Next
    INDEX
    Explanations

    metadata

    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
    łej
    -0.83
    jema
    -0.83
    ランス
    -0.83
    евич
    -0.80
    fatalError
    -0.79
    霖
    -0.79
     Bühnen
    -0.76
    junior
    -0.76
    лово
    -0.76
    ffering
    -0.75
    POSITIVE LOGITS
     metadata
    2.97
    metadata
    2.39
     meta
    2.23
     additional
    2.06
     attributes
    1.99
    meta
    1.97
     Metadata
    1.94
     properties
    1.90
     tags
    1.86
    MetaData
    1.84
    Activations Density 0.156%

    No Known Activations