© 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. 110895
    Prev
    Next
    INDEX
    Explanations

    batch or lot numbers described

    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
    heitsbild
    -0.80
    kowitz
    -0.78
    amblea
    -0.74
     война
    -0.72
    quese
    -0.72
     войне
    -0.71
     レザー
    -0.71
     arrayed
    -0.71
    价格
    -0.69
    ikon
    -0.68
    POSITIVE LOGITS
     batch
    5.53
     batches
    4.53
    batch
    4.44
     Batch
    4.13
    Batch
    4.09
    BATCH
    3.27
     BATCH
    3.19
     lot
    2.98
    batches
    2.97
    批
    2.78
    Activations Density 0.082%

    No Known Activations