© 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. 83870
    Prev
    Next
    INDEX
    Explanations

    investment professionals

    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
     fund
    -1.06
     Fund
    -0.88
     customers
    -0.85
     funds
    -0.83
    obat
    -0.77
    Fund
    -0.75
    InsertCommand
    -0.74
    брать
    -0.74
    𝑟
    -0.71
     services
    -0.71
    POSITIVE LOGITS
    floxacin
    0.85
     poème
    0.83
     phénomène
    0.82
     ($(
    0.78
     disposent
    0.77
    ยก
    0.76
     principais
    0.76
    andan
    0.75
     Courant
    0.74
     aident
    0.73
    Activations Density 0.028%

    No Known Activations