© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 120036
    Prev
    Next
    INDEX
    Explanations

    what is it

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

    The neuron fires on prominent content words that serve as the main topic or heading of a segment (e.g. “peptide,” “NativeScript,” “pediatric,” “Crown Point,” “Uploading”).

    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
     Maak
    -1.59
    ulfon
    -1.55
    }\
    -1.55
    ’
    -1.55
    ah
    -1.55
    此
    -1.54
    …”
    -1.53
    {\
    -1.52
    ib
    -1.49
    :
    -1.48
    POSITIVE LOGITS
     or
    2.17
    二日
    1.91
    contacto
    1.91
    Those
    1.87
     acoged
    1.80
     through
    1.75
     negociaciones
    1.74
     what
    1.73
    で一番
    1.70
     สวย
    1.70
    Activations Density 0.001%

    No Known Activations