© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58704
    Prev
    Next
    INDEX
    Explanations

    more than ever

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

    The neuron flags words and phrases that convey strong emphasis or extreme degree (comparatives/superlatives and intensifiers like “more,” “than ever,” “crucial,” “vital,” “important,” 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
     motivadoras
    -1.00
    delingen
    -1.00
    Much
    -0.94
    lepší
    -0.93
    푘
    -0.92
     much
    -0.92
    delà
    -0.91
     echt
    -0.90
    的其他
    -0.90
     graciosas
    -0.88
    POSITIVE LOGITS
     more
    2.98
     più
    1.65
     более
    1.62
    more
    1.55
     than
    1.54
     více
    1.49
     hơn
    1.46
     więcej
    1.46
     stronger
    1.42
     أكثر
    1.42
    Activations Density 0.049%

    No Known Activations