© 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. 77491
    Prev
    Next
    INDEX
    Explanations

    actions steps measures taken

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

    The neuron fires on words and phrases that describe recommended or possible actions—i.e. instructions or “steps you can take.”

    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
    จาก
    -1.02
    Есть
    -1.02
     chiên
    -0.99
    CREATED
    -0.93
     trầm
    -0.92
    Мето
    -0.91
    Répondre
    -0.90
    ận
    -0.90
    Еще
    -0.90
    　　《
    -0.89
    POSITIVE LOGITS
     taken
    2.67
    taken
    1.72
     TAKEN
    1.65
    Taken
    1.63
     Taken
    1.53
     to
    1.52
     tomada
    1.47
     against
    1.41
     measures
    1.39
     tomadas
    1.32
    Activations Density 0.024%

    No Known Activations