© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15833
    Prev
    Next
    INDEX
    Explanations

    emphasizing descriptions

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

    The neuron activates on the emphatic adverb “particularly,” flagging instances of that intensifier.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    และ
    -2.16
    ⡦
    -1.94
    蟊
    -1.82
    enangan
    -1.80
    褙
    -1.80
     avenir
    -1.77
     baloncesto
    -1.77
    uded
    -1.76
     esquí
    -1.76
    抟
    -1.74
    POSITIVE LOGITS
    '
    2.16
    i
    1.78
    k
    1.70
    b
    1.64
     wymiar
    1.58
    Because
    1.55
     partic
    1.52
    re
    1.47
    Especially
    1.45
     zwłaszcza
    1.45
    Activations Density 0.022%

    No Known Activations