© 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. 102374
    Prev
    Next
    INDEX
    Explanations

    source of things

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

    The neuron strongly activates on occurrences of the preposition “from.”

    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
     it
    -2.02
    蜴
    -1.73
     competitivos
    -1.56
     अलग
    -1.47
     UPDATED
    -1.45
     profundos
    -1.45
    늄
    -1.45
     utilizzando
    -1.43
     facendo
    -1.41
    Skocz
    -1.41
    POSITIVE LOGITS
    0
    2.30
    8
    2.27
    {
    1.98
    5
    1.81
     wciąż
    1.71
    那我
    1.70
    7
    1.70
     અને
    1.70
    栳
    1.62
    謌
    1.62
    Activations Density 0.053%

    No Known Activations