© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6535
    Prev
    Next
    INDEX
    Explanations

    beautiful or beautifully

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

    The neuron fires on positive, aesthetic adjectives (especially “beautiful” and similar praise words) describing something as appealing or high‐quality.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    excellent
    0.82
    PrimaryKey
    0.66
     отлич
    0.64
    靂
    0.64
     питание
    0.63
    αιρε
    0.63
     khiển
    0.62
    𝔾
    0.62
     люби
    0.62
     excelente
    0.62
    POSITIVE LOGITS
    งาม
    0.90
     plumage
    0.82
    ly
    0.81
     poised
    0.72
     blouses
    0.71
    umes
    0.70
     tapestry
    0.69
     melody
    0.68
     flowers
    0.67
     crafted
    0.67
    Activations Density 0.327%

    No Known Activations