© 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. 89842
    Prev
    Next
    INDEX
    Explanations

    designer or design

    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
     końcu
    -0.90
     jeżeli
    -0.88
     stellt
    -0.84
     französ
    -0.83
     prostor
    -0.81
     ملي
    -0.80
    >):
    -0.80
    吗
    -0.78
    libc
    -0.78
     Füßen
    -0.78
    POSITIVE LOGITS
    душка
    0.89
     toki
    0.88
     bales
    0.84
     osal
    0.82
     filmi
    0.81
    fael
    0.80
     Résumé
    0.80
     vache
    0.80
    嘯
    0.78
    પ
    0.77
    Activations Density 0.003%

    No Known Activations