© 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. 205080
    Prev
    Next
    INDEX
    Explanations

    monthly average

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

    special characters and structure

    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
     Đường
    0.64
    ໄປ
    0.63
    பை
    0.61
    ப
    0.60
    பு
    0.59
    దేశ
    0.54
     GoObject
    0.52
    岧
    0.52
     Coupon
    0.52
    𝗕
    0.52
    POSITIVE LOGITS
    uma
    0.62
    0.57
    eg
    0.56
    au
    0.55
     l
    0.53
     =
    0.52
     :
    0.52
    em
    0.52
    add
    0.52
    ins
    0.52
    Activations Density 0.000%

    No Known Activations