© 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. 50841
    Prev
    Next
    INDEX
    Explanations

    code statement terminator

    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
    세대
    0.47
     vertebr
    0.47
    чис
    0.47
    уд
    0.45
    бро
    0.42
     universo
    0.41
    лет
    0.40
    ниц
    0.40
    焜
    0.40
    ід
    0.39
    POSITIVE LOGITS
     ৫১
    0.46
     અલગ
    0.42
     আলাদা
    0.40
     ৫
    0.39
     স্বীকৃতি
    0.39
    onerror
    0.39
     sobre
    0.38
     জোরে
    0.38
     Foire
    0.38
     Board
    0.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.