© 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. 1493
    Prev
    Next
    INDEX
    Explanations

    reactive protein and conflict

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

    words and phrases related to conflict or competition, such as "fight", "struggle", "compete", "quarrels", or "reactive".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on words that describe conflict or competition (e.g. struggle, fight, compete, quarrel, challenge).

    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
    趼
    -2.48
    鸲
    -1.99
    眛
    -1.98
    titial
    -1.96
    櫺
    -1.88
     effekt
    -1.87
    臜
    -1.82
    蠃
    -1.81
    ﱠ
    -1.78
    ଃ
    -1.78
    POSITIVE LOGITS
    </u>
    1.95
     on
    1.68
     gesagt
    1.63
    On
    1.63
    但是
    1.61
     numerose
    1.56
    味道
    1.53
    焌
    1.52
    líben
    1.52
     seperti
    1.52
    Activations Density 0.002%

    No Known Activations