© 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. 12038
    Prev
    Next
    INDEX
    Explanations

    split, divide, partition, segment

    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
    "}";
    -0.82
    ciling
    -0.78
    لاف
    -0.72
    setPosition
    -0.72
    ňa
    -0.72
    ર્
    -0.71
    tividad
    -0.69
    emplos
    -0.69
    чиком
    -0.69
    imą
    -0.69
    POSITIVE LOGITS
     split
    4.78
    split
    4.16
     divided
    4.13
     splitting
    3.98
    Split
    3.83
     splits
    3.77
     Split
    3.73
     divide
    3.70
     divides
    3.41
    分割
    3.31
    Activations Density 0.264%

    No Known Activations