© 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. 5652
    Prev
    Next
    INDEX
    Explanations

    prepositions of location and direction

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

    location prepositions

    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
     physiologically
    0.21
    삵
    0.20
    萧
    0.19
    高品質
    0.19
     consequ
    0.19
     diminu
    0.18
     covariant
    0.18
    氨
    0.18
    使用
    0.18
    增加
    0.18
    POSITIVE LOGITS
     the
    0.35
     nearby
    0.35
    nearby
    0.28
     مسجد
    0.26
     downtown
    0.25
     Masjid
    0.24
     Hotel
    0.24
     Chinatown
    0.23
     Lake
    0.23
     학교
    0.22
    Activations Density 0.437%

    No Known Activations