© 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. 26371
    Prev
    Next
    INDEX
    Explanations

    climate change impacts

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

    increasing frequency and intensity of extreme weather

    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
    萦
    0.48
    亿元
    0.47
    缘
    0.45
    Gosudarstvennyj
    0.44
    欝
    0.44
    贯彻
    0.44
    甾
    0.44
    道德
    0.44
    ięcy
    0.44
    骷
    0.43
    POSITIVE LOGITS
     climate
    0.88
     climatic
    0.75
     climates
    0.74
     droughts
    0.74
    climate
    0.71
     जलवायु
    0.68
     warming
    0.66
     future
    0.66
     adaptation
    0.66
     resilience
    0.66
    Activations Density 0.045%

    No Known Activations