© 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. 90165
    Prev
    Next
    INDEX
    Explanations

    sea of

    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
     ocean
    -1.55
     seawater
    -1.34
    海洋
    -1.19
     oceans
    -1.13
     aquatic
    -1.12
     OCEAN
    -1.10
     seashore
    -1.05
    ocean
    -1.03
     seaside
    -1.03
    Aquatic
    -0.99
    POSITIVE LOGITS
    floor
    0.87
     calm
    0.84
    hores
    0.83
    漬
    0.82
     Murakami
    0.78
    front
    0.75
     zdarma
    0.75
    ms
    0.75
    JSONObject
    0.74
    mitz
    0.74
    Activations Density 0.023%

    No Known Activations