© 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. 68064
    Prev
    Next
    INDEX
    Explanations

    finding cheap tickets, medicine, GIFs

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

    here's how

    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
    จัดการ
    0.54
     ulterior
    0.52
     ล
    0.50
     Tuti
    0.48
     ತ
    0.47
     chemo
    0.47
     Sudden
    0.47
    ५
    0.46
    ข่าว
    0.46
    も
    0.46
    POSITIVE LOGITS
    pev
    0.48
    as
    0.47
    lom
    0.47
    wait
    0.46
    at
    0.46
    rom
    0.46
    p
    0.45
    they
    0.44
    preds
    0.44
    lon
    0.43
    Activations Density 0.002%

    No Known Activations