© 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. 1206
    Prev
    Next
    INDEX
    Explanations

    location and relationship prepositions

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

    prepositions indicating location, time, or manner

    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
     अभिकथन
    0.35
     চেয়ার
    0.30
     如果
    0.30
     }),
    0.29
     আয়নের
    0.29
    CLUDED
    0.28
     删除
    0.28
    }+\
    0.28
     អ្នក
    0.28
     असतील
    0.28
    POSITIVE LOGITS
     both
    0.31
    www
    0.27
     the
    0.26
    ри
    0.26
     compulsive
    0.25
    from
    0.25
    inthe
    0.25
    -
    0.25
    Baca
    0.25
    жи
    0.24
    Activations Density 0.723%

    No Known Activations