© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32000
    Prev
    Next
    INDEX
    Explanations

    html tags or newline separators

    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>
    -1.77
    ,”
    -1.65
    ,"
    -1.28
    ...),
    -1.03
    `),
    -1.01
    ),”
    -0.97
     ones
    -0.96
    凌天
    -0.94
    \",\
    -0.93
    蜻
    -0.93
    POSITIVE LOGITS
    <h2>
    8.13
    "){
    2.56
    <h3>
    2.44
    (){
    2.39
    ){
    2.36
    」。
    2.33
    "/>
    2.20
    》。
    2.17
    '){
    2.16
    </h2>
    2.14
    Activations Density 0.063%

    No Known Activations