© 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. 108959
    Prev
    Next
    INDEX
    Explanations

    this time

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

    when today

    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
    aisy
    0.43
     l
    0.40
     dopiero
    0.40
     নিয়েছেন
    0.38
     როგორც
    0.37
     ق
    0.37
    UIApplication
    0.36
     dần
    0.36
     C
    0.34
     sund
    0.34
    POSITIVE LOGITS
     यावेळी
    1.53
     during
    1.40
    今回は
    1.37
    此次
    1.31
     이번
    1.30
     이날
    1.30
    這次
    1.30
     tijdens
    1.28
     durante
    1.27
     এদিন
    1.27
    Activations Density 0.599%

    No Known Activations