© 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. 123737
    Prev
    Next
    INDEX
    Explanations

    listing common items

    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
    '
    -2.09
     или
    -1.86
     —
    -1.66
     anadolu
    -1.63
     språk
    -1.55
     parfüm
    -1.54
     hittar
    -1.50
    \
    -1.48
     spela
    -1.46
    してしまった
    -1.46
    POSITIVE LOGITS
     you
    2.34
    ⅝
    1.76
    ↵↵
    1.74
    と思いますが
    1.70
     umfang
    1.65
    ほか
    1.62
    yelitis
    1.61
    R
    1.59
     ¨
    1.59
    蔼
    1.54
    Activations Density 0.209%

    No Known Activations