© 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. 81512
    Prev
    Next
    INDEX
    Explanations

    holder, enclosure, puppy, bedroom furniture

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

    common ranges

    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
    mAb
    0.52
    簧
    0.50
    mM
    0.50
    波动
    0.49
    JU
    0.48
    اح
    0.48
    lL
    0.48
    眶
    0.47
    斋
    0.47
    NavBar
    0.46
    POSITIVE LOGITS
     manufacturers
    0.56
     ስርዓ
    0.55
     protection
    0.54
     capitalists
    0.50
     fabricantes
    0.49
     companies
    0.49
     orderly
    0.48
     manufacturer
    0.48
     durable
    0.48
     sensible
    0.47
    Activations Density 0.000%

    No Known Activations