© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 80990
    Prev
    Next
    INDEX
    Explanations

    expressions of liking or love

    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
    pantalón
    -0.92
     then
    -0.91
     guidelines
    -0.89
     beloved
    -0.89
     instead
    -0.89
    领域
    -0.85
     Lycée
    -0.82
     !==
    -0.81
     guideline
    -0.81
     Yandex
    -0.80
    POSITIVE LOGITS
     especially
    2.08
     especialmente
    1.68
     особенно
    1.66
    especially
    1.62
    Especially
    1.60
    尤其是
    1.53
     Especially
    1.48
     erity
    1.47
     particularly
    1.30
     Особенно
    1.30
    Activations Density 0.035%

    No Known Activations