© 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. 20768
    Prev
    Next
    INDEX
    Explanations

    search engine optimisation

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

    The neuron strongly activates on mentions of “search engine” (and its plural form) in the text.

    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
     been
    -1.94
     seperti
    -1.88
    䨻
    -1.75
    熠
    -1.74
    栳
    -1.72
    使得
    -1.70
     was
    -1.68
    ︐
    -1.66
     we
    -1.66
     alrededores
    -1.66
    POSITIVE LOGITS
     memutus
    2.14
     melap
    2.09
    </h3>
    1.95
     १
    1.92
    B
    1.88
     २०
    1.84
    ୌ
    1.80
    in
    1.80
    ri
    1.79
    la
    1.79
    Activations Density 0.003%

    No Known Activations