© 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. 34-GEMMASCOPE-RES-131K
    7. 1049
    Prev
    Next
    INDEX
    Explanations

    site selection

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

    The neuron activates on high-level corporate or marketing jargon—especially formal mission-statement language about “revealing underlying connections,” “shaping the future,” and similar business-health-tech buzzphrases.

    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
    ühm
    -0.90
     Disconnect
    -0.84
    んでいる
    -0.80
    ositol
    -0.80
    OURCE
    -0.80
    zieży
    -0.78
     einiges
    -0.78
    ená
    -0.77
    osome
    -0.76
    ALIA
    -0.75
    POSITIVE LOGITS
     location
    2.63
     locating
    2.55
     locations
    2.48
     siting
    2.11
     locate
    2.03
    locations
    2.03
    location
    1.98
     Locations
    1.92
     Location
    1.91
     Standort
    1.88
    Activations Density 0.031%

    No Known Activations