© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63339
    Prev
    Next
    INDEX
    Explanations

    diving and swimming events

    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
     spoke
    -0.78
     courir
    -0.73
     speak
    -0.72
     flattery
    -0.68
     lic
    -0.68
     strum
    -0.66
     aisles
    -0.66
     bipolar
    -0.64
    验证
    -0.64
     speaks
    -0.64
    POSITIVE LOGITS
     diving
    2.05
     Diving
    1.70
    diving
    1.64
     dive
    1.63
    Diving
    1.51
     dives
    1.47
     divers
    1.30
    dive
    1.25
     Dive
    1.19
     synchronized
    1.17
    Activations Density 0.009%

    No Known Activations