Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 0
    Prev
    Next
    INDEX
    Explanations

    the definite article followed by a noun

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

    the word "The" at the beginning of sentences in encyclopedic or technical articles.

    oai_token-act-pair · claude-4-5-haikuTriggered by @hijohnnylinnewwww
    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
    ⎔
    -1.78
    쐈
    -1.78
     RECEIVED
    -1.77
    椟
    -1.66
    菒
    -1.66
    あんまり
    -1.65
     princí
    -1.64
     THINGS
    -1.63
    rfan
    -1.63
     ARISING
    -1.60
    POSITIVE LOGITS
     of
    2.23
     from
    1.98
     with
    1.88
     has
    1.83
     at
    1.70
     There
    1.66
     by
    1.66
     between
    1.52
     parlar
    1.48
     new
    1.47
    Activations Density 0.077%

    No Known Activations