© 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. 109517
    Prev
    Next
    INDEX
    Explanations

    card or width

    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
     Michel
    -0.85
    Michel
    -0.84
     sensations
    -0.84
     Michelle
    -0.83
    Michelle
    -0.82
     PB
    -0.81
     сотрудники
    -0.81
     Bib
    -0.81
    快
    -0.75
     sensation
    -0.75
    POSITIVE LOGITS
    addToCart
    0.88
    一張
    0.82
     specialmente
    0.79
     wider
    0.79
    幢
    0.77
    赚钱
    0.76
    ˠ
    0.75
     cusp
    0.75
     shadow
    0.74
     tilf
    0.73
    Activations Density 0.011%

    No Known Activations