© 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. 16-GEMMASCOPE-2-RES-16K
    7. 528
    Prev
    Next
    INDEX
    Explanations

    word boundaries and punctuation

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

    `cup`

    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_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ’
    0.15
    ki
    0.15
    pe
    0.14
    ও
    0.14
    yl
    0.14
    ál
    0.14
    ka
    0.13
    ya
    0.13
    ución
    0.13
    ong
    0.13
    POSITIVE LOGITS
     estamp
    0.12
    捒
    0.12
     flexion
    0.12
     турни
    0.12
     autograph
    0.12
     непотпуним
    0.11
    只限平日
    0.11
    atthakath
    0.11
     таки
    0.11
    سٹم
    0.11
    Activations Density 0.075%

    No Known Activations