© 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. 105370
    Prev
    Next
    INDEX
    Explanations

    love you to death

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

    The neuron is simply firing on the word “to” (i.e. the preposition “to” in “to X” constructions).

    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
     to
    -1.87
     from
    -1.65
     xxiv
    -1.55
     zijn
    -1.54
     igra
    -1.53
    getF
    -1.48
     incrí
    -1.48
     seperti
    -1.47
     設計
    -1.47
    魮
    -1.46
    POSITIVE LOGITS
    9
    1.73
     gespielt
    1.62
    6
    1.61
     
    1.58
    8
    1.58
     oferece
    1.55
    手下
    1.52
     gegangen
    1.50
    いえば
    1.49
     mantém
    1.49
    Activations Density 0.062%

    No Known Activations