© 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. 103689
    Prev
    Next
    INDEX
    Explanations

    words ending in -ing or -ed

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

    wild, concise, target, diverse, landscape, server, continued, promise

    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
    м
    0.49
    م
    0.49
     mencegah
    0.48
     stesso
    0.48
    י
    0.48
    아
    0.47
     предприя
    0.46
    ओ
    0.46
     empêcher
    0.46
    Questo
    0.46
    POSITIVE LOGITS
    ile
    0.50
    ze
    0.50
     Integrating
    0.49
    of
    0.48
    intensity
    0.48
     Impressions
    0.48
    ef
    0.47
    elled
    0.47
     Intensity
    0.47
    andi
    0.47
    Activations Density 0.001%

    No Known Activations