© 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. 31-GEMMASCOPE-2-RES-262K
    7. 127486
    Prev
    Next
    INDEX
    Explanations

    Whole30

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

    diet plans and daily schedules

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     olive
    0.48
     aromat
    0.48
    ");</
    0.45
     correspon
    0.45
     exalt
    0.44
     deniz
    0.44
     conduz
    0.44
     ipv
    0.43
     hydrophilic
    0.43
     nutrientes
    0.42
    POSITIVE LOGITS
    を聞
    0.52
     चिंता
    0.48
    最後に
    0.47
    ੁ
    0.46
    觅
    0.46
     রাতে
    0.46
    ам
    0.45
    TING
    0.44
     অম
    0.44
    শেষ
    0.44
    Activations Density 0.000%

    No Known Activations