© 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. 10-GEMMASCOPE-RES-131K
    7. 101845
    Prev
    Next
    INDEX
    Explanations

    loss of life or beliefs

    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_10/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
    There
    -1.93
    because
    -1.91
     heightened
    -1.84
     There
    -1.76
     on
    -1.67
    Because
    -1.66
     Almost
    -1.66
     furthering
    -1.63
     because
    -1.60
     Because
    -1.60
    POSITIVE LOGITS
     senza
    2.05
    ྄
    1.76
     realmente
    1.73
    2
    1.73
     vraiment
    1.73
     colossal
    1.66
     dokun
    1.65
    really
    1.65
     splendid
    1.63
     veya
    1.61
    Activations Density 0.011%

    No Known Activations