© 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. 199246
    Prev
    Next
    INDEX
    Explanations

    foreign words and special characters

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

    correction and clarification

    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
    Vid
    0.48
    +"
    0.47
    来自
    0.46
     ultraf
    0.45
    undefined
    0.45
    (<
    0.45
    muted
    0.44
    лери
    0.44
    αυ
    0.43
     fx
    0.43
    POSITIVE LOGITS
    宪
    0.52
     restlessness
    0.49
     Astrology
    0.46
     зака
    0.44
    embrance
    0.44
    ล
    0.44
    ట్లా
    0.42
    राज्यपाल
    0.42
    ohr
    0.41
     Hasht
    0.41
    Activations Density 0.000%

    No Known Activations