© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93134
    Prev
    Next
    INDEX
    Explanations

    embell or decorate

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron responds to words about decorating or embellishing—terms for adornment and decorative treatments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    absorption
    -0.89
    (",");
    -0.75
    ねば
    -0.74
    に合わせて
    -0.73
    unregister
    -0.73
    Meghan
    -0.71
    łę
    -0.70
     déplacements
    -0.69
    дке
    -0.69
    Marilyn
    -0.68
    POSITIVE LOGITS
     decoration
    5.28
     decorate
    5.19
     decorated
    5.00
     decorating
    4.78
     decorations
    4.75
    Decor
    4.16
     Decor
    3.95
     decor
    3.91
    decoration
    3.86
    decorated
    3.83
    Activations Density 0.063%

    No Known Activations