© 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. 60333
    Prev
    Next
    INDEX
    Explanations

    introduction sections

    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
     Apesar
    -0.94
    reis
    -0.94
     Quiero
    -0.93
     SILVER
    -0.90
    despite
    -0.88
     sembla
    -0.87
    icii
    -0.87
     kuiten
    -0.86
    Sherman
    -0.85
     wavy
    -0.85
    POSITIVE LOGITS
     contribution
    1.05
     financial
    0.96
     and
    0.95
     ethical
    0.93
     on
    0.91
    Author
    0.91
     ethics
    0.89
     funding
    0.86
     limitations
    0.86
     conflicts
    0.86
    Activations Density 0.013%

    No Known Activations