© 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. 17489
    Prev
    Next
    INDEX
    Explanations

    hurricane followed by impact on homes

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

    hurricanes and cyclones

    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
     ماشین
    0.51
     bioquímica
    0.51
    缬
    0.51
    的服务
    0.50
    环境中
    0.49
    气氛
    0.49
    样品
    0.48
    亩
    0.48
    ༡
    0.48
    ㎎
    0.48
    POSITIVE LOGITS
     landfall
    0.92
     hurricane
    0.89
     Hurricane
    0.83
    hurricane
    0.78
     hurricanes
    0.73
    Hurricane
    0.72
     cyclone
    0.69
     Hurricanes
    0.67
     tornadoes
    0.65
     cyclones
    0.64
    Activations Density 0.046%

    No Known Activations