© 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. 10-GEMMASCOPE-RES-131K
    7. 65120
    Prev
    Next
    INDEX
    Explanations

    hockey, oxidases, Senior Cup

    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_10/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
    最初の
    -1.15
     achtergrond
    -1.02
    Medien
    -1.01
    ︺
    -0.99
     interesante
    -0.99
    hubung
    -0.98
     mennes
    -0.98
    enneth
    -0.97
     familières
    -0.96
     glaubte
    -0.96
    POSITIVE LOGITS
     bronzo
    1.33
    裃
    1.22
     oscu
    1.14
     Rumania
    1.10
     Primaria
    1.10
     mesi
    1.09
     kilom
    1.09
     vasi
    1.09
     abbiamo
    1.08
     prelude
    1.08
    Activations Density 0.059%

    No Known Activations