© 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. 91293
    Prev
    Next
    INDEX
    Explanations

    LaTeX math and lines

    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
    CONTAINER
    -0.92
     since
    -0.79
    expandafter
    -0.79
     by
    -0.77
    をはじめ
    -0.75
     Schmerzen
    -0.75
    omento
    -0.75
    /*/
    -0.73
     Slovensku
    -0.73
     bı
    -0.72
    POSITIVE LOGITS
    hline
    1.02
     ruled
    1.02
     lines
    0.91
     vzd
    0.85
     invisible
    0.85
     tenha
    0.84
    LINES
    0.84
     lignes
    0.83
    itatis
    0.82
     linhas
    0.82
    Activations Density 0.002%

    No Known Activations