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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52596
    Prev
    Next
    INDEX
    Explanations

    busYard DumpsterMaking SenseterminationLoading Plantwhat makes

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

    words ending in "ational" or followed by "Identifier" or "Messenger"

    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
     يؤ
    0.46
     í
    0.45
     片
    0.44
     軍
    0.44
     पोशा
    0.44
     assuming
    0.43
     toată
    0.43
     ユ
    0.43
     両
    0.43
     র
    0.42
    POSITIVE LOGITS
    лін
    0.50
    Cape
    0.48
    གས་
    0.48
     Essen
    0.48
    Overse
    0.48
    Sight
    0.48
     bilin
    0.46
    넋
    0.45
    Bali
    0.45
    등
    0.45
    Activations Density 0.000%

    No Known Activations