© 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. 129974
    Prev
    Next
    INDEX
    Explanations

    phrase ending in 'more' or 'disease'

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

    The neuron responds strongly to prominent content-bearing tokens—proper names, technical terms, titles or headings—flagging words that serve as key labels or topics in a document.

    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
     other
    -1.56
    .
    -1.48
     of
    -1.40
     Other
    -1.36
     innych
    -1.31
     других
    -1.31
    其它
    -1.30
    Other
    -1.28
    ではある
    -1.27
    其他
    -1.25
    POSITIVE LOGITS
     limpio
    1.49
     your
    1.35
     mengatakan
    1.31
     esimerkiksi
    1.25
     kuhusu
    1.24
     břez
    1.24
     maybe
    1.23
     Ukuran
    1.23
     Selasa
    1.23
     Tentang
    1.21
    Activations Density 0.111%

    No Known Activations