© 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-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83080
    Prev
    Next
    INDEX
    Explanations

    weather observations

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

    The neuron strongly responds to technical meteorological and weather‐forecasting terminology (e.g. “surface,” “analysis,” “chart,” “wind,” “pressure,” “forecasting,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    airbnb
    -0.77
    。『
    -0.76
     洗
    -0.72
    eapp
    -0.70
     pitch
    -0.70
     predstav
    -0.69
     Pitch
    -0.69
    默
    -0.68
    gettyimages
    -0.68
    ôtel
    -0.68
    POSITIVE LOGITS
     observations
    1.44
     observation
    1.27
    observations
    1.08
     Observations
    1.06
    SYN
    1.05
    Observation
    1.05
    observation
    1.04
     Observation
    1.02
    Observations
    1.01
    obs
    0.98
    Activations Density 0.021%

    No Known Activations