© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59714
    Prev
    Next
    INDEX
    Explanations

    "Go" followed by verbs

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

    The neuron specializes in spotting the imperative “Go,” especially when it introduces a call-to-action or link (“Go to…,” “Go back…,” 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_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
     också
    -1.78
    riezmann
    -1.70
     поэтому
    -1.65
    ৫
    -1.65
    ệu
    -1.58
    izate
    -1.57
    buds
    -1.54
     גם
    -1.54
    hells
    -1.54
    al
    -1.51
    POSITIVE LOGITS
    nang
    1.65
    You
    1.65
    aculture
    1.60
    1
    1.57
     первой
    1.54
    Thirty
    1.52
     lhes
    1.50
    ichteten
    1.50
    aktus
    1.48
    รวจ
    1.48
    Activations Density 0.011%

    No Known Activations