© 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. 100882
    Prev
    Next
    INDEX
    Explanations

    scientific names and place names

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

    The neuron is detecting scientific Latin taxonomic names (genus/species or other formal organism 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
     you
    -1.88
    ℣
    -1.65
     perder
    -1.59
    了一個
    -1.52
    ykjav
    -1.45
    与此
    -1.45
    这样一个
    -1.43
     one
    -1.43
     listos
    -1.43
     "
    -1.42
    POSITIVE LOGITS
    不要
    1.64
    /
    1.52
    。”
    1.51
     doar
    1.49
    //
    1.48
    。
    1.48
     altes
    1.47
    只
    1.47
    “
    1.44
    、
    1.42
    Activations Density 0.324%

    No Known Activations