© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69647
    Prev
    Next
    INDEX
    Explanations

    specific noun phrases

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

    the neuron highlights content-bearing nouns and verbs that name the main subject or object (key topics) in a sentence.

    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
     itinéraires
    -1.54
     perfecte
    -1.52
     totale
    -1.48
     heu
    -1.46
    allez
    -1.46
    乁
    -1.45
     direc
    -1.44
    featuring
    -1.43
     ijs
    -1.42
     materie
    -1.41
    POSITIVE LOGITS
     at
    2.09
     by
    2.05
     also
    1.84
     During
    1.48
     not
    1.46
     for
    1.45
     set
    1.45
     Much
    1.45
     each
    1.45
     Even
    1.43
    Activations Density 0.124%

    No Known Activations