© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3170
    Prev
    Next
    INDEX
    Explanations

    elegant aesthetic

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

    elegant cinematic romantic exquisite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
     objecting
    0.46
    趄
    0.46
     Intensity
    0.45
    摀
    0.44
     deficit
    0.44
     enforceable
    0.44
    承認
    0.42
     स्वीकृत
    0.42
     Objection
    0.42
    訃
    0.42
    POSITIVE LOGITS
    优雅
    0.96
    精致
    0.92
    细腻
    0.88
    精彩
    0.85
    清新
    0.85
    创意
    0.82
    气质
    0.82
    展现
    0.80
    韵
    0.80
    浪漫
    0.80
    Activations Density 0.060%

    No Known Activations