© 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. 115818
    Prev
    Next
    INDEX
    Explanations

    programming language constructs

    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
     even
    -1.02
     incluso
    -0.94
    nö
    -0.91
     entweder
    -0.91
     Oliveira
    -0.90
    以前
    -0.90
    пион
    -0.90
    レビュー
    -0.88
     ²
    -0.87
    图书
    -0.86
    POSITIVE LOGITS
     kwiaty
    1.00
    Allora
    0.92
     звезда
    0.91
     złota
    0.90
    フィール
    0.89
     нему
    0.88
    trois
    0.86
    hésitez
    0.85
    hmen
    0.85
     acreditar
    0.85
    Activations Density 0.046%

    No Known Activations