© 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. 260986
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    гістра
    0.52
    いくつか
    0.48
    文献
    0.47
    έν
    0.46
    ર્ગ
    0.46
    ਨ
    0.45
    літ
    0.45
    事務所
    0.45
     সঙ্ক
    0.45
     scrimmage
    0.44
    POSITIVE LOGITS
    apeutic
    0.51
     suces
    0.50
     cient
    0.46
    जूदा
    0.46
     seeks
    0.46
     sering
    0.46
    에는
    0.45
     desist
    0.45
    ाराम
    0.44
    ѕ
    0.43
    Activations Density 0.001%

    No Known Activations