© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60388
    Prev
    Next
    INDEX
    Explanations

    geo-strategic planners

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

    This neuron detects news‐style metadata and attributions—things like bylines, datelines, and organization or agency names.

    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
     wouldn
    -0.94
    Wouldn
    -0.91
     aujourd
    -0.85
     Wouldn
    -0.84
     says
    -0.82
    Argu
    -0.79
    麩
    -0.78
    Outcomes
    -0.78
    legi
    -0.76
    覧
    -0.76
    POSITIVE LOGITS
     begun
    0.93
    écoute
    0.91
     demonstrated
    0.90
    บัติ
    0.88
    ΤΗ
    0.85
     since
    0.83
    maar
    0.82
    +|
    0.82
     retos
    0.81
     rostro
    0.81
    Activations Density 0.003%

    No Known Activations