© 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. 103530
    Prev
    Next
    INDEX
    Explanations

    social media and education

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

    linked with cryptocurrency and complexity

    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
    ០
    0.62
    válto
    0.55
    nú
    0.55
    któ
    0.53
    ení
    0.52
    adás
    0.51
     нашего
    0.50
    ília
    0.50
    ๐
    0.50
     ਤਾਂ
    0.49
    POSITIVE LOGITS
     biggest
    0.55
     hobby
    0.54
     strategic
    0.52
     primitive
    0.50
     largest
    0.50
     pragmatic
    0.50
     auxiliary
    0.49
     difficulties
    0.48
     subsidiary
    0.48
     mainframe
    0.48
    Activations Density 0.000%

    No Known Activations