© 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. 185249
    Prev
    Next
    INDEX
    Explanations

    expect given

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

    categories vs. producers

    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
    Ⅼ
    0.53
     समायोजित
    0.48
     शिखर
    0.46
     युव
    0.46
     Δια
    0.46
     ማን
    0.46
    າມາດ
    0.45
    后期
    0.45
     கடை
    0.44
     달라
    0.44
    POSITIVE LOGITS
     toegang
    0.52
    0.47
    '-
    0.45
     inductively
    0.45
    -
    0.45
     dengan
    0.44
     oxidation
    0.44
     powerful
    0.44
    your
    0.43
    ahassee
    0.43
    Activations Density 0.000%

    No Known Activations