© 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. 129619
    Prev
    Next
    INDEX
    Explanations

    paid courses or training

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

    cracked, coup, book, acquisitions

    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
     محبوب
    0.56
    ید
    0.54
    になった
    0.50
    م
    0.48
    на
    0.47
    rocytes
    0.47
    と同じ
    0.46
     زمین
    0.46
    ہ
    0.45
    ール
    0.45
    POSITIVE LOGITS
     financ
    0.52
     infused
    0.49
     ICT
    0.45
     anticipated
    0.44
     cae
    0.44
     infringement
    0.44
     Chartered
    0.44
     Completed
    0.43
     copyrights
    0.43
     monetary
    0.43
    Activations Density 0.000%

    No Known Activations