© 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. 93876
    Prev
    Next
    INDEX
    Explanations

    code with functions and maps

    np_acts-logits-general · gemini-2.5-flash-lite
    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>
    -1.20
    particularly
    -0.92
    教你
    -0.90
     particularly
    -0.85
     eran
    -0.79
    funded
    -0.79
    ])
    -0.77
    </th>
    -0.77
    ⎟
    -0.75
    setdefault
    -0.74
    POSITIVE LOGITS
    <h2>
    4.31
    ){
    3.50
    (){
    3.47
    "){
    3.30
    ){
    
    3.00
    '){
    2.97
    ")){
    2.83
    }){
    2.63
    (){
    
    2.59
    )){
    2.58
    Activations Density 0.304%

    No Known Activations