© 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. 66639
    Prev
    Next
    INDEX
    Explanations

    not to followed by action verbs

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

    The neuron consistently fires on the token “to,” i.e. the infinitive marker/preposition “to” in the text.

    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
    お昼
    -2.30
     Reſ
    -2.20
    あっという
    -2.16
    ዡ
    -2.09
     中式
    -2.05
     comanda
    -2.03
    🅃
    -2.00
     tende
    -1.97
    快適
    -1.94
    涇
    -1.94
    POSITIVE LOGITS
    ları
    1.85
     in
    1.82
    ла
    1.81
    ться
    1.77
    橙
    1.70
    ())->
    1.66
     своем
    1.66
    <i>
    1.65
     zarówno
    1.64
    </strong>
    1.63
    Activations Density 0.003%

    No Known Activations