© 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. 81609
    Prev
    Next
    INDEX
    Explanations

    paths starting with '../../', '../', and './js/'

    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
    飯店
    -0.73
     вже
    -0.72
    tachten
    -0.72
     frågor
    -0.72
    lanzen
    -0.71
    报表
    -0.71
     IAEA
    -0.71
     levure
    -0.71
     įsi
    -0.71
     Recognizing
    -0.70
    POSITIVE LOGITS
    formik
    0.92
    Données
    0.87
     ieder
    0.85
    른
    0.83
     kultur
    0.82
    ╥
    0.81
     tui
    0.80
     fokus
    0.80
    miro
    0.79
     Sensei
    0.77
    Activations Density 0.062%

    No Known Activations