© 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. 220741
    Prev
    Next
    INDEX
    Explanations

    gypsum impacts, trips to dump, wealth

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

    Syrian, company distributes

    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
    Not in Any Lists

    No Comments

    Negative Logits
     അല്ലെങ്കിൽ
    0.49
    หรือ
    0.47
     או
    0.47
     কিংবা
    0.47
     ወይም
    0.47
     ਜਾਂ
    0.45
     י
    0.42
     კ
    0.42
     किंवा
    0.42
     მს
    0.42
    POSITIVE LOGITS
     wurden
    0.54
    :
    0.53
    :`
    0.48
     dissidents
    0.44
    ষে
    0.44
     :/
    0.43
     AAC
    0.42
     downregulated
    0.42
     licences
    0.42
    ната
    0.41
    Activations Density 0.002%

    No Known Activations