© 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. 10-GEMMASCOPE-RES-131K
    7. 124083
    Prev
    Next
    INDEX
    Explanations

    checkweighman, checkbox, CHECK_EQ

    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
     Its
    -1.94
     Anyone
    -1.90
     止
    -1.87
     enchanting
    -1.86
     empleo
    -1.78
     schien
    -1.77
    哙
    -1.75
     sagrado
    -1.73
     idyllic
    -1.73
     amelior
    -1.70
    POSITIVE LOGITS
    7
    2.17
    4
    2.11
    if
    2.11
    0
    2.09
    9
    2.05
    5
    2.03
    which
    1.98
     fald
    1.97
    2
    1.95
    in
    1.91
    Activations Density 0.028%

    No Known Activations