© 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. 103180
    Prev
    Next
    INDEX
    Explanations

    Brookings Institution, openshift, Union address

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

    the word "OpenShift" (specifically the token "shift" in "OpenShift").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron detects named entities—proper names of standards, organizations, products, or other technical labels.

    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
     and
    -1.98
     Because
    -1.90
     After
    -1.82
    擱
    -1.78
     invigor
    -1.77
     cerdas
    -1.76
     Forty
    -1.75
     At
    -1.75
     Many
    -1.74
     Almost
    -1.69
    POSITIVE LOGITS
    簠
    1.98
    ⩖
    1.88
    湏
    1.80
    꿩
    1.80
     mediocre
    1.78
     his
    1.77
    笵
    1.75
    ーズン
    1.72
     unabhängig
    1.71
    燹
    1.70
    Activations Density 0.013%

    No Known Activations