© 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. 10-GEMMASCOPE-RES-131K
    7. 39316
    Prev
    Next
    INDEX
    Explanations

    Miss Universe, submit, honour, factor

    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_10/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
     différents
    -1.76
     GETTING
    -1.69
     !!!!!
    -1.48
     fiasco
    -1.47
    really
    -1.44
     geolog
    -1.43
     Ukraina
    -1.42
     抠
    -1.42
    
    -1.41
     cursus
    -1.40
    POSITIVE LOGITS
     first
    2.44
     three
    2.36
     Since
    2.23
     There
    2.22
     four
    2.19
     by
    2.17
     five
    1.98
     Despite
    1.98
     seven
    1.98
     two
    1.95
    Activations Density 0.130%

    No Known Activations