© 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. 34-GEMMASCOPE-RES-131K
    7. 91810
    Prev
    Next
    INDEX
    Explanations

    See the NOTICE file

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

    The neuron strongly activates on very common English function words (e.g. “to,” “the,” “of,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     alene
    -0.94
    ˠ
    -0.81
    ⌇
    -0.78
     courteous
    -0.77
    amentul
    -0.75
    illant
    -0.73
     thù
    -0.73
     seul
    -0.73
    Vocab
    -0.73
    готовления
    -0.73
    POSITIVE LOGITS
    šení
    0.87
     حسب
    0.85
    Apologies
    0.82
    美しい
    0.79
    圧倒
    0.75
     лице
    0.75
     поси
    0.74
     notices
    0.73
     sewage
    0.71
    此刻
    0.71
    Activations Density 0.141%

    No Known Activations