© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47578
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations from lists

    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
     did
    -1.03
     萬
    -1.03
     llamado
    -0.91
    所に
    -0.87
    ⑪
    -0.85
    ҂
    -0.85
     suivez
    -0.84
    Did
    -0.83
    ﹕
    -0.83
     so
    -0.82
    POSITIVE LOGITS
     abbreviation
    1.21
     acronym
    1.17
    izator
    1.06
    जब
    1.03
    很多人
    1.02
    Efter
    1.01
     urgente
    0.98
    بدأ
    0.96
     notícia
    0.94
    cargador
    0.94
    Activations Density 0.190%

    No Known Activations