© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 87024
    Prev
    Next
    INDEX
    Explanations

    for [someone/thing described]

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

    The neuron consistently activates on the standalone word “for,” flagging occurrences of that preposition.

    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
    вгений
    -2.06
     IBRARY
    -2.00
    螄
    -1.97
     especiais
    -1.90
     perchè
    -1.89
    ⎆
    -1.84
    臜
    -1.82
    蘼
    -1.76
    белый
    -1.73
     :");
    -1.72
    POSITIVE LOGITS
     you
    2.78
    ;
    2.05
    {
    2.05
    ₱
    1.76
    ?
    1.76
     discern
    1.76
     NO
    1.73
    肫
    1.73
    いない
    1.73
     people
    1.73
    Activations Density 0.018%

    No Known Activations