© 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. 220760
    Prev
    Next
    INDEX
    Explanations

    real estate but any GmbH

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

    undergoing transformation or development

    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
    к
    0.53
    ADO
    0.50
    RAY
    0.49
    EDA
    0.49
    uzi
    0.49
    ianz
    0.48
    Sight
    0.48
    sight
    0.47
    ixel
    0.47
    ULA
    0.46
    POSITIVE LOGITS
    誣
    0.57
     alopecia
    0.52
     scoreless
    0.51
     insolvent
    0.50
     durante
    0.50
     abdominal
    0.49
     idempot
    0.48
     заболеваний
    0.48
     inade
    0.47
     empt
    0.47
    Activations Density 0.000%

    No Known Activations