© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85961
    Prev
    Next
    INDEX
    Explanations

    programming annotations and technical terms

    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_10/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
     ܐ
    -1.23
     firent
    -1.20
    poň
    -1.16
     hemd
    -1.16
     spion
    -1.16
    bably
    -1.16
     ananas
    -1.15
    沵
    -1.14
     annen
    -1.13
    かっこいい
    -1.13
    POSITIVE LOGITS
     these
    2.38
     prices
    1.77
    这些
    1.64
    These
    1.63
     those
    1.60
     services
    1.51
     their
    1.51
     employee
    1.46
    Since
    1.41
     price
    1.36
    Activations Density 0.006%

    No Known Activations