© 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. 22-GEMMASCOPE-RES-131K
    7. 39049
    Prev
    Next
    INDEX
    Explanations

    citations and abbreviations containing numbers

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects short uppercase sequences—acronyms, abbreviations, and reference codes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     on
    -1.25
     in
    -1.06
     號
    -0.95
     like
    -0.91
    獺
    -0.90
     it
    -0.88
     hubungan
    -0.87
    Parfait
    -0.87
    longed
    -0.86
    鑑賞
    -0.85
    POSITIVE LOGITS
    TeX
    1.25
    
    1.24
    neling
    1.23
    粜
    1.23
    ;';
    1.21
    рации
    1.18
     korte
    1.14
    umenter
    1.14
    êtement
    1.13
    CTION
    1.10
    Activations Density 0.016%

    No Known Activations