© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43603
    Prev
    Next
    INDEX
    Explanations

    word pairings

    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
     capricious
    -1.38
    "",
    -1.36
    ově
    -1.36
    逖
    -1.33
     persian
    -1.30
     majú
    -1.30
    然后再
    -1.30
     cavalier
    -1.28
    コチラ
    -1.26
    と話
    -1.24
    POSITIVE LOGITS
    ׇ
    1.41
     they
    1.33
     вместо
    1.29
     Instead
    1.21
     without
    1.20
    さんの
    1.18
    เพราะ
    1.16
     prominent
    1.15
     over
    1.14
     emphasize
    1.14
    Activations Density 0.003%

    No Known Activations