© 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. 56809
    Prev
    Next
    INDEX
    Explanations

    numbers followed by time units

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

    carry burdens

    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
    Not in Any Lists

    No Comments

    Negative Logits
    𝟏
    0.49
     выбирать
    0.47
     einfacher
    0.47
    チ
    0.45
     limitar
    0.45
     hopelessness
    0.45
    🧹
    0.44
    ጀት
    0.44
    ચી
    0.44
     veramente
    0.44
    POSITIVE LOGITS
     Archaeological
    0.54
     Archae
    0.52
     Aboriginal
    0.47
     Religious
    0.47
     religious
    0.46
     tải
    0.45
     archaeological
    0.45
     Predators
    0.44
     Māori
    0.44
     hứng
    0.43
    Activations Density 0.000%

    No Known Activations