© 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. 10-GEMMASCOPE-RES-131K
    4. 9742
    Prev
    Next
    INDEX
    Explanations

    wildland fires

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

    The neuron detects mentions of fires (e.g., “fire,” “fires,” “wildfires”) in the text.

    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
    饪
    -2.70
    ܖ
    -2.47
    ’
    -2.44
    ſſen
    -2.34
    philosop
    -2.23
    ୈ
    -2.22
    涠
    -2.20
    厯
    -2.20
     estadounid
    -2.17
    嵎
    -2.17
    POSITIVE LOGITS
    </strong>
    2.47
    They
    2.41
     Allowing
    2.20
    Приготовление
    2.20
     manchmal
    2.08
    Zubereitung
    2.08
     тысячи
    2.06
     $
    2.06
     To
    2.05
     важ
    1.98
    Activations Density 0.009%

    No Known Activations