© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93448
    Prev
    Next
    INDEX
    Explanations

    words starting with op

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

    The neuron strongly activates on tokens beginning with the letters “Op” (i.e. the substring “Op” at the start of a token).

    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
    glomer
    -0.89
     Editing
    -0.81
    𝓊
    -0.75
    penet
    -0.73
     essentially
    -0.71
     sympathetic
    -0.71
    voyage
    -0.70
     绘
    -0.70
    營業
    -0.70
     skilled
    -0.69
    POSITIVE LOGITS
     op
    1.08
     OP
    1.04
     Winfrey
    1.01
    Op
    0.94
     Op
    0.91
    nion
    0.86
    op
    0.80
     żół
    0.79
     Opa
    0.77
     opa
    0.77
    Activations Density 0.064%

    No Known Activations