© 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. 22-GEMMASCOPE-RES-131K
    7. 95327
    Prev
    Next
    INDEX
    Explanations

    statistical and code constructs

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

    The neuron responds to terms that introduce or specify quantities, counts, or events—words like “random,” “number,” “event,” “for,” “each,” and “between.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    orgt
    -0.96
    nesty
    -0.90
     ბ
    -0.84
    ΰ
    -0.82
     Wiltshire
    -0.82
     cursory
    -0.82
    ormon
    -0.81
    кер
    -0.80
    INDOW
    -0.79
     cũ
    -0.79
    POSITIVE LOGITS
    Khach
    0.91
    Véxase
    0.90
    Bisa
    0.87
     communiquez
    0.83
     fisio
    0.83
     exceeding
    0.82
     secundarios
    0.82
     almost
    0.81
    </h2>
    0.80
    ادل
    0.79
    Activations Density 0.029%

    No Known Activations