© 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. 249826
    Prev
    Next
    INDEX
    Explanations

    SME make, original packaging

    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
     υψη
    0.48
     après
    0.47
     غیر
    0.47
    Caf
    0.47
    㕩
    0.47
     页
    0.45
     عالمی
    0.45
    ές
    0.44
     አን
    0.44
     উচ্চ
    0.44
    POSITIVE LOGITS
    ‍या
    0.56
    o
    0.53
    落地
    0.50
     dele
    0.47
    ंधरा
    0.43
    imble
    0.42
    PARAM
    0.42
    dele
    0.42
    ❽
    0.42
    вак
    0.41
    Activations Density 0.000%

    No Known Activations