© 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. 185756
    Prev
    Next
    INDEX
    Explanations

    numbers, percentages, or units

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

    pronouns asking questions and stating facts

    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
    idded
    0.46
    noff
    0.45
     yanıt
    0.44
     또한
    0.43
    AUC
    0.42
    ᴢ
    0.42
     zgod
    0.42
    귿
    0.42
     상당
    0.41
    agues
    0.41
    POSITIVE LOGITS
     url
    0.48
    ן
    0.48
    בע
    0.48
    メニュー
    0.47
    薀
    0.47
     น้ำ
    0.47
     Tables
    0.47
    កម្ម
    0.47
     junk
    0.46
     moduli
    0.46
    Activations Density 0.000%

    No Known Activations