© 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. 70619
    Prev
    Next
    INDEX
    Explanations

    Enron email headers

    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
     diciembre
    -1.01
     ended
    -1.01
     where
    -0.98
     its
    -0.94
     noviembre
    -0.91
    xdb
    -0.88
     after
    -0.88
     cafetería
    -0.87
     Straße
    -0.86
     at
    -0.85
    POSITIVE LOGITS
    ኧ
    0.97
    somewhat
    0.92
    phalt
    0.90
     aiuto
    0.90
    nicy
    0.89
    鵙
    0.87
    <>());
    0.86
    Apologies
    0.84
     migli
    0.84
    Océ
    0.84
    Activations Density 0.010%

    No Known Activations