© 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. 212208
    Prev
    Next
    INDEX
    Explanations

    cutlery cup

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

    new/added/increased

    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
    他們
    0.57
    他们
    0.51
    饮食
    0.49
    然后
    0.49
    विद्या
    0.49
    íns
    0.48
    ☘
    0.48
    election
    0.47
    爱
    0.47
    íd
    0.45
    POSITIVE LOGITS
     neue
    0.55
     nuova
    0.54
    جیت
    0.52
     désormais
    0.51
     fairway
    0.50
     photom
    0.49
     meniscus
    0.49
     epicenter
    0.49
     طبق
    0.49
     recommended
    0.49
    Activations Density 0.001%

    No Known Activations