© 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. 139053
    Prev
    Next
    INDEX
    Explanations

    our, their, service, commodity, creating

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

    core-shell mixtures, support crowns, converting streams, rover tours

    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
    ля
    0.47
    ือ
    0.47
    虾
    0.45
    ЛЯ
    0.44
    ศ
    0.44
    밈
    0.44
    лектро
    0.43
    력
    0.43
    饮食
    0.43
    낭
    0.42
    POSITIVE LOGITS
     സ്‌
    0.50
     sprinkling
    0.49
     dé
    0.48
     Tees
    0.48
     sûr
    0.47
     lm
    0.45
     Poincaré
    0.45
     réalisé
    0.44
    conf
    0.44
     LM
    0.44
    Activations Density 0.000%

    No Known Activations