© 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. 152792
    Prev
    Next
    INDEX
    Explanations

    CPE offering

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

    POM files and packages

    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
     C
    0.48
     Cancer
    0.45
     III
    0.45
     Jordan
    0.43
    <em>
    0.43
     Sin
    0.42
     I
    0.41
     parte
    0.41
     Daha
    0.41
    <start_of_image>
    0.40
    POSITIVE LOGITS
    ৬০
    0.51
    รุ่น
    0.51
     هذا
    0.50
    รวจ
    0.49
    ена
    0.47
    لای
    0.47
    živ
    0.45
    א
    0.44
    öglichkeiten
    0.44
    *=
    0.44
    Activations Density 0.000%

    No Known Activations