© 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. 108132
    Prev
    Next
    INDEX
    Explanations

    or perhaps, because, especially

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

    but, however, and

    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
     insidious
    0.54
     anastom
    0.48
    削減
    0.47
    dense
    0.47
     emargin
    0.47
     wsi
    0.46
    पोज
    0.43
    𝔰
    0.43
     activates
    0.43
     aligns
    0.43
    POSITIVE LOGITS
     כל
    0.53
    MouseEvent
    0.50
     المك
    0.46
     المل
    0.46
     সৌন্দর্য
    0.46
     குழந்தையின்
    0.46
     Prayer
    0.45
    Prayer
    0.45
     Perk
    0.44
    所有的
    0.44
    Activations Density 0.001%

    No Known Activations