© 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. 70288
    Prev
    Next
    INDEX
    Explanations

    web article URLs

    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
     such
    -1.20
     it
    -0.81
    zonego
    -0.78
    ncbi
    -0.75
    With
    -0.75
     had
    -0.73
     incorporate
    -0.73
    such
    -0.73
     történ
    -0.72
     таком
    -0.72
    POSITIVE LOGITS
    www
    2.89
     www
    2.27
     besto
    1.00
    Aplicaciones
    0.97
    Artículos
    0.94
    Www
    0.94
    原始内容存档
    0.92
    assets
    0.89
    ladelphia
    0.83
    Conclusiones
    0.83
    Activations Density 0.046%

    No Known Activations