© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113640
    Prev
    Next
    INDEX
    Explanations

    comparative limits

    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_10/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
     Diſ
    -1.81
     bensin
    -1.73
    鰨
    -1.70
    ·
    -1.69
     elefante
    -1.69
     bague
    -1.68
     parfüm
    -1.63
     desenli
    -1.63
    歘
    -1.63
     aktar
    -1.62
    POSITIVE LOGITS
     is
    1.77
     
    1.75
    ↵
    1.73
    "
    1.69
     zarówno
    1.62
     p
    1.51
    “
    1.48
     vergleich
    1.44
     están
    1.42
     at
    1.40
    Activations Density 0.017%

    No Known Activations