© 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. 22-GEMMASCOPE-RES-131K
    7. 28201
    Prev
    Next
    INDEX
    Explanations

    import statements and structure

    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_22/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
     integrar
    -0.88
     to
    -0.85
    しますね
    -0.85
    série
    -0.83
     elige
    -0.81
     Unfortunately
    -0.80
    Какво
    -0.80
     häufigsten
    -0.80
     Comunicação
    -0.79
     prič
    -0.79
    POSITIVE LOGITS
     nga
    0.87
     nguyen
    0.87
     jag
    0.84
    안
    0.84
     namen
    0.84
     Invitation
    0.84
    Ges
    0.84
     Sop
    0.83
    entreprise
    0.82
     MNRAS
    0.82
    Activations Density 0.012%

    No Known Activations