© 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. 72725
    Prev
    Next
    INDEX
    Explanations

    Marrakech

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

    examples, definitions, data types

    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
     clenched
    0.44
    т
    0.44
    ت
    0.43
    ে
    0.41
     outre
    0.41
     borrower
    0.41
    Declar
    0.41
    で
    0.41
     patients
    0.40
    一
    0.40
    POSITIVE LOGITS
    这意味着
    0.49
     কূপ
    0.45
    داشت
    0.45
     jobId
    0.45
     chữ
    0.44
     EJ
    0.43
    旗舰
    0.43
     felicidad
    0.42
     Elec
    0.42
     (${
    0.42
    Activations Density 0.000%

    No Known Activations