© 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. 10-GEMMASCOPE-RES-131K
    7. 20226
    Prev
    Next
    INDEX
    Explanations

    ever more or further

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

    The neuron strongly activates on comparative intensifiers—especially occurrences of the word “more.”

    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
    䊐
    -1.77
    į
    -1.63
    </h4>
    -1.61
    圌
    -1.59
    EVERY
    -1.58
     تمامی
    -1.55
     &
    -1.53
    could
    -1.52
    颡
    -1.52
    ࿊
    -1.52
    POSITIVE LOGITS
    because
    2.00
    棪
    2.00
    Because
    1.78
    他的
    1.78
     because
    1.60
     υπάρχ
    1.59
    Some
    1.57
     people
    1.53
     two
    1.52
    Two
    1.47
    Activations Density 0.006%

    No Known Activations