© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21519
    Prev
    Next
    INDEX
    Explanations

    NSObject

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

    The neuron strongly activates on capitalized proper names and named entities (people, places, organizations, classes, etc.).

    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
    罴
    -2.83
     serán
    -2.77
     Then
    -2.77
     relativamente
    -2.75
     yalnızca
    -2.66
     yaklaşık
    -2.63
     tendrán
    -2.56
     permiten
    -2.52
     aparentemente
    -2.50
     podrían
    -2.47
    POSITIVE LOGITS
    s
    3.25
    *
    2.86
    0
    2.77
     sebagai
    2.67
     atau
    2.66
    猻
    2.59
    e
    2.58
    just
    2.58
    ⬯
    2.56
     男人
    2.53
    Activations Density 0.027%

    No Known Activations