© 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. 45317
    Prev
    Next
    INDEX
    Explanations

    financial and programming terms

    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
    臨床
    -0.85
     остается
    -0.81
    [*]
    -0.80
    ￣
    -0.76
    IZATION
    -0.76
    不管
    -0.73
    複数
    -0.73
     daß
    -0.73
     execute
    -0.72
     muß
    -0.72
    POSITIVE LOGITS
     specialist
    1.00
     businesses
    0.92
    แรง
    0.85
    prepareStatement
    0.83
     forecasts
    0.83
    Dette
    0.82
    AZIONI
    0.82
     dislikes
    0.82
    Businesses
    0.81
     gefällt
    0.80
    Activations Density 0.001%

    No Known Activations