© 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. 25921
    Prev
    Next
    INDEX
    Explanations

    British and English creative professionals

    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
    izate
    -1.09
    lizes
    -1.05
     LIABLE
    -0.98
    Groet
    -0.97
     saia
    -0.96
    preneurs
    -0.96
    izat
    -0.96
    锹
    -0.95
    lhe
    -0.94
    ENIA
    -0.91
    POSITIVE LOGITS
     actor
    2.03
     writer
    2.02
     singer
    1.96
     actress
    1.95
     poet
    1.86
     journalist
    1.86
     musician
    1.84
     artist
    1.78
     author
    1.66
     historian
    1.64
    Activations Density 0.142%

    No Known Activations