© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102410
    Prev
    Next
    INDEX
    Explanations

    a noun

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

    The neuron flags instances of the indefinite article “a” (and by extension “an”).

    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
    netje
    -2.02
    ⟣
    -1.74
     excellente
    -1.68
     
    -1.68
     italien
    -1.68
     annon
    -1.68
     unrival
    -1.59
     Ô
    -1.57
    OKAY
    -1.56
     surtout
    -1.55
    POSITIVE LOGITS
     this
    3.08
     that
    2.91
     these
    2.50
     from
    2.47
     such
    2.28
     with
    2.22
     other
    2.17
     those
    2.16
     which
    2.14
     our
    2.08
    Activations Density 0.214%

    No Known Activations