© 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. 34-GEMMASCOPE-RES-131K
    7. 92941
    Prev
    Next
    INDEX
    Explanations

    national defense strategy acquisition

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

    The neuron strongly activates on the headline or top‐of‐page title text (including subtitle and “Read More” links) rather than on the body content.

    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
    Už
    -0.93
    deployment
    -0.85
     Tanjung
    -0.82
     deployment
    -0.82
    Boris
    -0.81
    vatten
    -0.81
    Tujuan
    -0.80
    schul
    -0.80
     skeletons
    -0.80
     smoothie
    -0.80
    POSITIVE LOGITS
     my
    0.83
    嵌
    0.81
    isive
    0.79
     synchronize
    0.79
     Synchronization
    0.79
     our
    0.76
     contested
    0.76
     Conditions
    0.75
     derrot
    0.75
     наш
    0.73
    Activations Density 0.028%

    No Known Activations