© 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. 107688
    Prev
    Next
    INDEX
    Explanations

    task force

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

    The neuron is tuned to detect mentions of “task force” (i.e. occurrences of the phrase Task Force).

    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
    ludes
    -0.77
     strongest
    -0.75
     Cobb
    -0.73
     Medley
    -0.73
     Least
    -0.70
    Gc
    -0.70
     fuertes
    -0.70
     entidades
    -0.69
    Nid
    -0.69
     melding
    -0.69
    POSITIVE LOGITS
     force
    1.80
    force
    1.74
     Force
    1.58
    Force
    1.47
     forces
    1.38
    FORCE
    1.38
    forces
    1.29
     Forces
    1.17
     FORCE
    1.08
     fuerza
    1.07
    Activations Density 0.033%

    No Known Activations