© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 128110
    Prev
    Next
    INDEX
    Explanations

    Feng Shui principles

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

    saving $

    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
    Not in Any Lists

    No Comments

    Negative Logits
    0.47
    (
    0.47
    UC
    0.46
    Gust
    0.46
    Acc
    0.44
    ра
    0.44
    Due
    0.43
    ř
    0.43
    Interestingly
    0.43
    Clock
    0.42
    POSITIVE LOGITS
     писатель
    0.49
    <unused31>
    0.48
    ভৌম
    0.48
     অভিযান
    0.47
     специальные
    0.47
     专业
    0.46
     وړاندوینه
    0.45
    িক্ষে
    0.45
     বিদ্রোহীদের
    0.45
     interventi
    0.44
    Activations Density 0.001%

    No Known Activations