© 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. 4305
    Prev
    Next
    INDEX
    Explanations

    chunking and batching

    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
    ForAll
    -0.88
    所有的
    -0.82
    resiasi
    -0.79
    erschrank
    -0.76
    đe
    -0.74
     飾
    -0.74
    pepe
    -0.73
    除此之外
    -0.73
     داشتم
    -0.72
    ėjimo
    -0.71
    POSITIVE LOGITS
     chunk
    2.59
    chunk
    2.39
     batch
    2.36
     chunks
    2.19
    Chunk
    2.11
    batch
    2.09
     batches
    2.03
    Batch
    1.78
    CHUNK
    1.73
     Batch
    1.73
    Activations Density 0.048%

    No Known Activations