© 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. 34-GEMMASCOPE-RES-131K
    7. 102896
    Prev
    Next
    INDEX
    Explanations

    keywords followed by separators like = : (

    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
    Ia
    -0.95
    气势
    -0.94
    着了
    -0.94
    ってた
    -0.93
    ==""){
    -0.89
    づけ
    -0.88
     composants
    -0.87
     feuilles
    -0.87
    žius
    -0.87
    inių
    -0.86
    POSITIVE LOGITS
     figliu
    1.20
     other
    1.20
    ೫
    1.09
    jangkau
    1.09
     אף
    1.05
    Although
    1.02
    定食
    1.02
     Although
    1.01
     sogenannten
    1.00
    Bewer
    0.99
    Activations Density 0.027%

    No Known Activations