© 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. 4571
    Prev
    Next
    INDEX
    Explanations

    Su followed by suite or succession

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

    sexually suggestive business suit

    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
    marshalO
    0.38
    oglio
    0.38
    霰
    0.37
    ক্ষিপ্ত
    0.37
    DanhMucSP
    0.36
     Германия
    0.36
    㡷
    0.36
    ሽን
    0.36
    ొప్పి
    0.36
     nirvach
    0.36
    POSITIVE LOGITS
     SU
    3.41
    Su
    3.31
     Su
    3.25
     су
    3.16
    SU
    3.16
    苏
    3.16
     Су
    3.11
     su
    3.06
    su
    3.06
    蘇
    3.05
    Activations Density 0.219%

    No Known Activations