© 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. 116931
    Prev
    Next
    INDEX
    Explanations

    prominent, successful, leading entities

    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
     poudre
    -1.04
     tradicional
    -1.02
     farine
    -1.01
     vanille
    -0.98
     sés
    -0.97
     goû
    -0.96
     cuillère
    -0.96
     planche
    -0.95
     maille
    -0.95
     pendekatan
    -0.94
    POSITIVE LOGITS
     respected
    1.52
     force
    1.43
     viable
    1.42
     worthy
    1.40
     dominant
    1.25
     successful
    1.23
     premier
    1.22
     contender
    1.20
     player
    1.16
     recognized
    1.16
    Activations Density 0.058%

    No Known Activations