© 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. 66225
    Prev
    Next
    INDEX
    Explanations

    beautiful, gorgeous, lovely

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

    The neuron is picking out present-tense descriptive verbs and modals used to comment or evaluate (e.g. “sparkling,” “may,” “look,” “provide,” “sounds”).

    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
    大満足
    -0.90
    YourGuide
    -0.87
    🦭
    -0.79
    APE
    -0.76
    uj
    -0.75
     iyi
    -0.75
    oid
    -0.75
    ὀ
    -0.75
    PRO
    -0.74
    FileDescriptor
    -0.74
    POSITIVE LOGITS
     beautiful
    5.63
    Beautiful
    4.03
    beautiful
    4.00
     Beautiful
    3.92
     gorgeous
    3.52
     BEAUTIFUL
    3.44
     đẹp
    3.22
     krás
    3.20
     краси
    3.13
     lovely
    3.03
    Activations Density 0.108%

    No Known Activations