© 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. 118554
    Prev
    Next
    INDEX
    Explanations

    C/C++ and VBA code keywords

    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
    pso
    -0.92
    ETHODS
    -0.91
     グラフ
    -0.90
    akteur
    -0.88
     meanwhile
    -0.87
    колко
    -0.87
     incluyen
    -0.86
    RTSN
    -0.85
    あとは
    -0.85
    その他の
    -0.85
    POSITIVE LOGITS
    ～」
    0.90
    zten
    0.89
     again
    0.88
    ----+
    0.85
     Hache
    0.84
    ysaccharide
    0.84
     they
    0.84
    ادا
    0.83
    TRACE
    0.83
     placa
    0.83
    Activations Density 0.015%

    No Known Activations