© 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. 139701
    Prev
    Next
    INDEX
    Explanations

    documents, athletes, nature

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

    Older technology, marriage certificate, non-spherical

    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
     отклю
    0.50
    咊
    0.50
    ขนาด
    0.49
     dział
    0.48
    ين
    0.48
    ћа
    0.47
    퇸
    0.47
    铊
    0.47
    DataXYZ
    0.46
     হর
    0.46
    POSITIVE LOGITS
     seekers
    0.46
     compress
    0.44
    urers
    0.44
    csv
    0.43
     unfriendly
    0.43
     strained
    0.42
     concealed
    0.42
     compressed
    0.41
     ureth
    0.41
     ਪ
    0.40
    Activations Density 0.002%

    No Known Activations