© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 61116
    Prev
    Next
    INDEX
    Explanations

    revenue commissioner or security investigations

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

    The neuron is looking for named entities—proper names, brands, model numbers, organizations, titles, and similar capitalized terms.

    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
     manquer
    -1.81
     unveils
    -1.78
     créer
    -1.72
     huiles
    -1.71
     revamped
    -1.70
     fiasco
    -1.70
     poign
    -1.68
     accentu
    -1.66
    ,;
    -1.63
     THOSE
    -1.58
    POSITIVE LOGITS
     with
    2.23
     after
    2.05
     not
    2.05
     several
    1.86
     some
    1.78
     using
    1.72
     as
    1.71
     because
    1.69
     seven
    1.66
     in
    1.64
    Activations Density 5.579%

    No Known Activations