© 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. 22-GEMMASCOPE-RES-131K
    7. 40364
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

    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_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
     lisäksi
    -0.82
     sogar
    -0.81
     those
    -0.79
     US
    -0.78
    甚至
    -0.78
    茴
    -0.78
    льних
    -0.77
    tamina
    -0.77
     OFFICES
    -0.77
    se
    -0.75
    POSITIVE LOGITS
    áctica
    1.05
    bringung
    0.97
     omgeving
    0.95
     онъ
    0.93
    тием
    0.91
    ῇ
    0.90
     producción
    0.90
     and
    0.90
     reputación
    0.89
     pomá
    0.88
    Activations Density 0.061%

    No Known Activations