© 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. 10-GEMMASCOPE-RES-131K
    7. 20538
    Prev
    Next
    INDEX
    Explanations

    foreign words and specific terms

    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
     Every
    -2.30
     Each
    -2.27
     Both
    -2.16
     on
    -2.09
     each
    -2.03
     L
    -2.00
     and
    -1.98
     D
    -1.95
     M
    -1.94
     Also
    -1.94
    POSITIVE LOGITS
     ingenting
    2.02
    櫺
    1.86
     problemet
    1.86
    Beweg
    1.85
    Liefer
    1.82
    閖
    1.80
     NEGRO
    1.80
    CONCLUS
    1.77
     dekoratif
    1.77
    ឪ
    1.76
    Activations Density 0.012%

    No Known Activations