© 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. 22-GEMMASCOPE-RES-131K
    7. 130953
    Prev
    Next
    INDEX
    Explanations

    extract format

    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
     both
    -2.25
     beiden
    -1.79
    Both
    -1.75
     two
    -1.75
     beide
    -1.69
    both
    -1.64
     Both
    -1.57
     ambos
    -1.57
     keduanya
    -1.55
    BOTH
    -1.53
    POSITIVE LOGITS
     all
    1.48
     όλα
    1.34
     tất
    1.32
     kaikki
    1.13
     telah
    1.05
     allemaal
    1.04
     tutte
    1.03
    Woah
    1.02
    のですね
    0.99
     semua
    0.99
    Activations Density 0.034%

    No Known Activations