© 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. 207344
    Prev
    Next
    INDEX
    Explanations

    badge milestones

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

    months and dates

    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
    Negative Logits
    اوی
    0.56
    тріш
    0.50
    زیز
    0.50
    Ethnic
    0.49
    作り
    0.49
    ズ
    0.48
     کردار
    0.48
    aise
    0.48
    ஆ
    0.47
     बहुतेक
    0.47
    POSITIVE LOGITS
     crossings
    0.51
     emphasized
    0.48
     timestamp
    0.46
     candlest
    0.46
     commemorate
    0.46
     crossed
    0.44
     crosses
    0.44
     emphasize
    0.44
     clas
    0.43
     prayed
    0.43
    Activations Density 0.001%

    No Known Activations