© 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
    2. Gemma-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 9543
    Prev
    Next
    INDEX
    Explanations

    increase in 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-2-1b-pt/resid_post/layer_22_width_16k_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
     gusts
    1.15
     storm
    1.10
    storm
    1.07
     thunderstorm
    1.01
    坡
    0.98
    速度
    0.98
     turbulence
    0.95
     velocity
    0.94
    storms
    0.93
    晨
    0.93
    POSITIVE LOGITS
     El
    1.20
    El
    1.15
     lanthan
    1.11
     La
    1.09
    La
    1.06
     Sahel
    0.95
     mån
    0.95
    Caracter
    0.88
    MathOperator
    0.88
    Beans
    0.87
    Activations Density 0.111%

    No Known Activations