© 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. 109639
    Prev
    Next
    INDEX
    Explanations

    rounded to nearest

    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
     because
    -0.96
    genden
    -0.85
     less
    -0.82
     or
    -0.79
     on
    -0.78
     not
    -0.77
     процес
    -0.75
    씹
    -0.75
     роботи
    -0.74
     (
    -0.74
    POSITIVE LOGITS
     nearest
    1.25
    Nearest
    1.07
    nearest
    1.03
     två
    0.93
     Nearest
    0.91
    で一番
    0.90
     niekoľ
    0.89
     najbli
    0.85
    ndig
    0.85
     interessante
    0.84
    Activations Density 0.005%

    No Known Activations