© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8388
    Prev
    Next
    INDEX
    Explanations

    what X do you have

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

    what kind of

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     যেভাবে
    0.46
    所の
    0.46
     happening
    0.44
    되는
    0.43
    锭
    0.43
    提出的
    0.43
     केलेल्या
    0.42
     જેવા
    0.41
    สิ่งที่
    0.41
    甸
    0.40
    POSITIVE LOGITS
     we
    0.82
     they
    0.79
     estamos
    0.73
     trzeba
    0.66
     você
    0.63
     corresponds
    0.63
     utilizamos
    0.63
     devemos
    0.61
     you
    0.61
     ਤੁਸੀਂ
    0.61
    Activations Density 0.201%

    No Known Activations