© 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. 60109
    Prev
    Next
    INDEX
    Explanations

    register and records

    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
     Funktions
    -0.71
     Gary
    -0.69
    资格
    -0.69
    Гц
    -0.68
    Literatuur
    -0.66
    otras
    -0.66
     informativo
    -0.66
     lẫn
    -0.66
     мәкалә
    -0.65
     confuso
    -0.65
    POSITIVE LOGITS
     book
    2.73
     books
    2.45
    book
    2.27
     libro
    2.00
     Book
    1.98
    books
    1.84
    Book
    1.84
     register
    1.84
     BOOK
    1.76
    Books
    1.69
    Activations Density 0.014%

    No Known Activations