© 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. 6858
    Prev
    Next
    INDEX
    Explanations

    horse racing terms and titles

    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
    他們的
    -0.89
     began
    -0.89
     their
    -0.87
     cumbersome
    -0.81
    他们的
    -0.80
     because
    -0.80
     said
    -0.79
     mainly
    -0.79
     нарушение
    -0.79
     Großbritannien
    -0.78
    POSITIVE LOGITS
    twice
    0.98
    deux
    0.94
     horloge
    0.90
     parcour
    0.89
     gespe
    0.88
    separated
    0.88
    吭
    0.88
     morceaux
    0.87
     Kranken
    0.87
     kabel
    0.87
    Activations Density 0.010%

    No Known Activations