© 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. 10-GEMMASCOPE-RES-131K
    7. 8774
    Prev
    Next
    INDEX
    Explanations

    U.S. Army branches and activities

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

    The neuron detects mentions of U.S. Army organizations, units, corps, ranks, and related military entity 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_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
    并没有
    -1.70
    </sup>
    -1.63
    ݯ
    -1.51
    ༛
    -1.45
     luy
    -1.44
     Cette
    -1.40
    </h2>
    -1.40
     pourraient
    -1.39
    </b>
    -1.38
     teo
    -1.38
    POSITIVE LOGITS
     on
    1.55
     allows
    1.53
     through
    1.52
     before
    1.49
     besonders
    1.47
     relatively
    1.41
     while
    1.39
    ．．．
    1.39
     insbesondere
    1.38
    velocityY
    1.38
    Activations Density 0.044%

    No Known Activations