© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111134
    Prev
    Next
    INDEX
    Explanations

    weather and terrain descriptors

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

    The neuron fires on descriptive weather-condition adjectives (e.g. rainy, windy, snowy).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    </td>
    -3.45
    </b>
    -2.78
     ''
    -2.67
    [
    -2.55
    ...
    -2.52
    }
    -2.52
     '
    -2.22
     $^{\
    -2.16
    ''
    -2.11
     ......
    -2.02
    POSITIVE LOGITS
    =’
    2.77
    蔸
    2.67
    </strong>
    2.64
    gucig
    2.63
    屺
    2.52
    踯
    2.52
    鹮
    2.39
    䛗
    2.38
    艄
    2.36
    椟
    2.34
    Activations Density 0.009%

    No Known Activations