© 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. 171879
    Prev
    Next
    INDEX
    Explanations

    time favorite, say yes, dive back

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

    seeking immortality

    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
    度的
    0.52
    m
    0.48
    e
    0.48
    َف
    0.47
    رو
    0.46
    儀
    0.46
    u
    0.45
    k
    0.44
     कहां
    0.43
    restrictions
    0.42
    POSITIVE LOGITS
    рсә
    0.52
    鸷
    0.49
     fumar
    0.47
     Obrigado
    0.46
     Festa
    0.45
     postcard
    0.45
    Marshaler
    0.45
    Budget
    0.45
     Poké
    0.45
     ফকির
    0.44
    Activations Density 0.000%

    No Known Activations