© 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. 221211
    Prev
    Next
    INDEX
    Explanations

    reservation

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

    destination, deserts, home, hitman

    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
    emment
    0.49
    iant
    0.47
    usions
    0.47
    телно
    0.47
    llr
    0.46
     ########.
    0.46
    alu
    0.46
    ভূমিতে
    0.46
    iens
    0.46
     пропуска
    0.45
    POSITIVE LOGITS
    ס
    0.50
    ری
    0.49
    ני
    0.47
     last
    0.46
    کی
    0.44
    ھر
    0.44
    رو
    0.43
    قی
    0.43
     hotel
    0.41
    န်
    0.41
    Activations Density 0.000%

    No Known Activations