© 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. 22-GEMMASCOPE-RES-131K
    4. 69259
    Prev
    Next
    INDEX
    Explanations

    weather and climate characteristics

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

    The neuron activates on words referring to weather or climatic/environmental conditions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    seamnă
    -1.24
    orsese
    -1.16
    }`);
    -1.16
    __).
    -1.09
    ']))
    -1.09
    }{
    -1.07
    ());
    -1.06
    }`}
    -1.05
    össä
    -1.05
    ]$
    -1.03
    POSITIVE LOGITS
     conditions
    2.08
     weather
    1.38
     factors
    1.27
     climate
    1.18
    conditions
    1.09
     favorable
    1.09
     condition
    1.08
     unfavourable
    1.06
     parameters
    1.05
     unfavorable
    1.04
    Activations Density 0.026%

    No Known Activations