© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 28920
    Prev
    Next
    INDEX
    Explanations

    ip addresses and spider

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

    The neuron is keyed to numeral tokens, especially those forming legal docket or case‐number sequences.

    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
     only
    -1.55
     tylko
    -1.33
     perdiendo
    -1.31
     аккура
    -1.30
    jemahan
    -1.29
     csak
    -1.27
    	
    -1.24
                
    -1.24
    credited
    -1.23
     только
    -1.21
    POSITIVE LOGITS
     (
    1.39
     then
    1.38
     they
    1.37
     **/
    
    1.35
    的
    1.31
    )){
    1.27
    tics
    1.26
     –
    1.26
     (“
    1.23
    neling
    1.21
    Activations Density 0.076%

    No Known Activations