© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46539
    Prev
    Next
    INDEX
    Explanations

    earthquake

    np_acts-logits-general · gemini-2.5-flash-lite

    earthquakes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     médecins
    0.53
     коюм
    0.52
    认定
    0.51
    荸
    0.51
    劳动
    0.50
    팻
    0.50
     पोस्टमार्टम
    0.50
    败
    0.50
    बच्चों
    0.49
     नियोक्ता
    0.49
    POSITIVE LOGITS
     seism
    1.21
     earthquake
    1.20
     Earthquake
    1.07
     earthquakes
    1.04
     seismic
    0.99
    地震
    0.98
     quake
    0.94
     terrem
    0.92
     ভূমিকম্প
    0.90
     earthqu
    0.87
    Activations Density 0.029%

    No Known Activations