© 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. 34509
    Prev
    Next
    INDEX
    Explanations

    Jeremy followed by a surname

    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
    '].
    -1.01
    ″]
    -0.88
    韩国
    -0.87
     особенно
    -0.83
     pul
    -0.81
     katholischen
    -0.80
     настолько
    -0.80
    至于
    -0.79
    眼鏡
    -0.79
     But
    -0.78
    POSITIVE LOGITS
     Suppl
    1.05
    が残
    1.05
     schauen
    1.00
     kogo
    1.00
     actuated
    0.94
     Royaume
    0.94
     plusieurs
    0.91
     dedicata
    0.90
     famiglie
    0.88
    WarningLevel
    0.88
    Activations Density 0.005%

    No Known Activations