© 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. 102363
    Prev
    Next
    INDEX
    Explanations

    example or page archival

    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
     札幌
    -0.82
    OnLoad
    -0.77
     valenci
    -0.77
     teman
    -0.76
    otypes
    -0.75
     günü
    -0.74
     Seward
    -0.73
    نسا
    -0.73
     vermeiden
    -0.73
     finner
    -0.72
    POSITIVE LOGITS
    ByExample
    1.27
    Example
    1.11
     example
    1.05
     Example
    1.01
    oredCriteria
    0.96
    Missouri
    0.93
     Joplin
    0.90
     Missouri
    0.84
    EXAMPLE
    0.84
     examples
    0.83
    Activations Density 0.002%

    No Known Activations