© 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. 109592
    Prev
    Next
    INDEX
    Explanations

    news agency names, former titles, corporations

    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
     “[
    -0.96
     Modelling
    -0.94
     nineteenth
    -0.94
     stoff
    -0.90
     twentieth
    -0.90
    Senator
    -0.89
     skut
    -0.88
     eier
    -0.88
     zade
    -0.87
     eighteenth
    -0.86
    POSITIVE LOGITS
    AP
    1.35
    ___
    1.29
     AP
    1.05
    ½
    0.99
     еще
    0.95
     Associated
    0.94
     nejak
    0.90
     isn
    0.88
    Associated
    0.86
     recognize
    0.86
    Activations Density 0.055%

    No Known Activations