© 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. 170395
    Prev
    Next
    INDEX
    Explanations

    legal proceedings

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

    forced ranking, buying, file paths, overly wordy

    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
     прозра
    0.48
    国
    0.46
    透明
    0.44
     бес
    0.42
    শস্ত্র
    0.41
     ఇతర
    0.41
     كافة
    0.41
     lainnya
    0.40
     brillantes
    0.40
    ◥
    0.40
    POSITIVE LOGITS
     Geet
    0.56
     leeway
    0.55
     Atul
    0.52
     Tendulkar
    0.51
     Phill
    0.49
     Nuss
    0.49
     Panch
    0.48
     Kõ
    0.47
    ercase
    0.47
     Thor
    0.46
    Activations Density 0.000%

    No Known Activations