Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98
    Prev
    Next
    INDEX
    Explanations

    Licensed under the Apache License

    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
    чники
    -0.88
     apprécié
    -0.86
     Imágenes
    -0.86
     poliester
    -0.86
    ίζει
    -0.84
    crane
    -0.83
    UNIDAD
    -0.81
     validés
    -0.81
    archiwizowane
    -0.81
     összefoglaló
    -0.81
    POSITIVE LOGITS
     zwar
    0.84
     sharply
    0.84
     पनि
    0.81
     after
    0.79
     plu
    0.77
    を開催
    0.75
     though
    0.73
     land
    0.73
     menu
    0.72
     posting
    0.72
    Activations Density 0.577%

    No Known Activations