© 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. 34-GEMMASCOPE-RES-131K
    4. 35005
    Prev
    Next
    INDEX
    Explanations

    HTML tags and code delimiters

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

    The neuron strongly activates on numerical tokens—years, scores, counts, and other digit‐based values.

    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
    </u>
    -1.30
    ,”
    -1.11
    </h4>
    -1.11
    ,"
    -0.90
    "],
    -0.81
    */}
    -0.78
    vician
    -0.77
    </th>
    -0.77
    люб
    -0.76
    essage
    -0.76
    POSITIVE LOGITS
    <h2>
    5.13
    》。
    1.60
    ")){
    1.48
    ]){
    1.48
    ){
    1.45
    ){
    
    1.44
    '){
    1.41
    (){
    1.40
    "){
    1.40
    )。
    1.39
    Activations Density 0.099%

    No Known Activations