© 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-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 16950
    Prev
    Next
    INDEX
    Explanations

    acne and pimples

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

    acne and breakouts

    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
    濡
    0.46
    劣化
    0.42
    👵
    0.41
    बर
    0.41
    platinum
    0.41
     CRC
    0.40
     তফস
    0.40
    bishop
    0.39
    لاف
    0.39
    =$\
    0.39
    POSITIVE LOGITS
     acne
    2.11
     pim
    2.05
     Acne
    2.03
     breakouts
    1.65
     Pim
    1.63
     ব্রণ
    1.59
     breakout
    1.54
    痤
    1.54
    pim
    1.53
    痘
    1.48
    Activations Density 0.064%

    No Known Activations