© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 4270
    Prev
    Next
    INDEX
    Explanations

    opposition, liability, or mathematical opposites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    行
    0.45
    ব
    0.43
     fácilmente
    0.43
     facilmente
    0.43
    спекти
    0.42
    ibraries
    0.41
    敉
    0.41
    掝
    0.41
    зы
    0.41
     dá
    0.41
    POSITIVE LOGITS
     Luego
    0.47
     Output
    0.43
     LIKE
    0.43
     Like
    0.42
     agreeing
    0.42
     adhesion
    0.41
     Pending
    0.41
     Outputs
    0.41
     -&
    0.41
     Approval
    0.41
    Activations Density 0.017%

    No Known Activations