© 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. 69959
    Prev
    Next
    INDEX
    Explanations

    mathematical definitions starting with 'let' or 'suppose'

    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
    plaat
    -0.98
    さんで
    -0.98
     kellett
    -0.93
     groter
    -0.92
    MessageTagHelper
    -0.90
    espé
    -0.89
    orienti
    -0.88
     इन
    -0.88
    🕶
    -0.87
     THESE
    -0.86
    POSITIVE LOGITS
     X
    0.95
     be
    0.92
     is
    0.88
     additionally
    0.88
     conversely
    0.86
     furthermore
    0.83
     взять
    0.83
     $
    0.82
     Schot
    0.81
    ській
    0.81
    Activations Density 0.060%

    No Known Activations