© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38489
    Prev
    Next
    INDEX
    Explanations

    explaining concepts and changes

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

    The neuron fires on the main content-bearing words of a sentence—i.e. the topic-relevant, information-dense nouns and technical terms.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    hicule
    -1.47
    着一个
    -1.45
     による
    -1.38
     you
    -1.38
    曖昧
    -1.37
    isation
    -1.37
     möglicherweise
    -1.33
    苙
    -1.31
    仕事を
    -1.30
    diseño
    -1.30
    POSITIVE LOGITS
     parfü
    1.83
     tjen
    1.58
     parfüm
    1.57
     medlem
    1.52
    这些
    1.52
     cirka
    1.52
    telah
    1.50
     gruppen
    1.47
    schw
    1.45
     regler
    1.42
    Activations Density 0.233%

    No Known Activations