© 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. 34-GEMMASCOPE-RES-131K
    7. 2264
    Prev
    Next
    INDEX
    Explanations

    census demographic data

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

    The neuron fires on sentence-final full stops, marking ends of sentences.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     daudz
    -1.00
     nếu
    -0.96
    Namara
    -0.94
    \}$,
    -0.91
    Cartney
    -0.84
    時から
    -0.83
     Nếu
    -0.81
     būs
    -0.80
    ;%%
    -0.80
     אם
    -0.80
    POSITIVE LOGITS
     it
    0.99
     here
    0.98
    ksz
    0.93
     farklı
    0.91
     substitutes
    0.88
     alimenti
    0.88
     It
    0.87
    Elektron
    0.86
    它的
    0.86
    良いです
    0.85
    Activations Density 0.003%

    No Known Activations