© 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. 13354
    Prev
    Next
    INDEX
    Explanations

    Welcome to

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

    The neuron responds specifically to the word “to,” i.e. it fires on the preposition “to.”

    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
     \\
    -1.90
     zdarma
    -1.77
     damaligen
    -1.66
     pomocí
    -1.63
     pomocou
    -1.59
     tomando
    -1.58
     każ
    -1.54
    '
    -1.53
     $
    -1.53
     лучшие
    -1.52
    POSITIVE LOGITS
     mereka
    1.92
     рецепта
    1.64
    后期
    1.59
     男孩
    1.55
     forState
    1.48
     христи
    1.48
     DialogResult
    1.48
     morfo
    1.48
     increíble
    1.45
    お部屋
    1.45
    Activations Density 0.009%

    No Known Activations