© 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. 10338
    Prev
    Next
    INDEX
    Explanations

    selection of items

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

    The neuron detects words in large‐quantity offerings phrases (e.g. “selection of,” “collection of,” “largest of”).

    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
     use
    -1.90
     you
    -1.86
     it
    -1.79
     utilizamos
    -1.75
     eenvou
    -1.71
     they
    -1.66
     seleccionamos
    -1.65
     usamos
    -1.65
     utilizados
    -1.60
     imágen
    -1.54
    POSITIVE LOGITS
     portugal
    1.63
     Therefore
    1.63
    ції
    1.62
     pietre
    1.62
    rón
    1.58
    Additionally
    1.57
     wees
    1.57
    !’
    1.56
    ”。
    1.54
    ！”
    1.52
    Activations Density 0.032%

    No Known Activations