© 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. 180267
    Prev
    Next
    INDEX
    Explanations

    and dental, continue to, walls in

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

    foreign language and specific English words

    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
     صنایع
    0.47
    Customers
    0.45
    HOUR
    0.45
    γων
    0.45
    ['_
    0.45
    Decedent
    0.44
    딤
    0.43
    waitForIdleSync
    0.43
    উৎ
    0.43
    चलिए
    0.42
    POSITIVE LOGITS
     hat
    0.47
    리고
    0.46
     음악
    0.45
     Jér
    0.44
    屏蔽
    0.44
    b
    0.43
     Uruguay
    0.43
     hét
    0.42
    vič
    0.42
     беше
    0.42
    Activations Density 0.000%

    No Known Activations