© 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. 66077
    Prev
    Next
    INDEX
    Explanations

    the TrumpetsThe AttorneyThe PointMy NotesSearch byThe presentActivists

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

    The neuron consistently activates on the capitalized word “The,” especially when it appears at the start of titles or headings.

    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
    Якщо
    -1.75
     keh
    -1.71
     importants
    -1.69
     dieu
    -1.62
     germain
    -1.61
     barres
    -1.59
     accessoires
    -1.59
     geene
    -1.56
     zir
    -1.55
     simpel
    -1.55
    POSITIVE LOGITS
     in
    1.81
     because
    1.79
     with
    1.70
     on
    1.59
    ↵↵
    1.59
     also
    1.59
     probably
    1.52
     out
    1.49
     
    1.46
     increased
    1.44
    Activations Density 0.000%

    No Known Activations