© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 70947
    Prev
    Next
    INDEX
    Explanations

    java io, nio, util imports

    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_22/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
    pantalón
    -1.75
     desfile
    -1.67
    鰨
    -1.65
     menikah
    -1.64
     bahagia
    -1.61
     sekarang
    -1.61
    Jawab
    -1.61
    pantalon
    -1.60
     unicórnio
    -1.59
     можна
    -1.58
    POSITIVE LOGITS
    e
    2.17
    T
    2.05
    O
    2.03
    M
    1.98
    B
    1.95
    N
    1.93
    L
    1.93
    F
    1.88
    ot
    1.87
    He
    1.87
    Activations Density 0.005%

    No Known Activations