© 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. 123834
    Prev
    Next
    INDEX
    Explanations

    VisualVM, Flight Recorder, deals with, !!! :, Walsh, Slovenian theatre, authors

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

    Data Mesh risks

    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
    挈
    0.57
    o
    0.54
    千
    0.51
    搏
    0.49
    噸
    0.47
    修建
    0.46
    膘
    0.46
    高級
    0.45
    shtml
    0.44
    千年
    0.44
    POSITIVE LOGITS
     mesures
    0.50
    Locked
    0.49
     auteurs
    0.48
     poets
    0.47
     responsables
    0.46
     marqu
    0.46
    }->
    0.46
     authors
    0.46
     Andrei
    0.45
    Connor
    0.45
    Activations Density 0.001%

    No Known Activations