© 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. 195547
    Prev
    Next
    INDEX
    Explanations

    prepositions and what follows

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

    if context is important

    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
    open
    0.45
    AF
    0.45
     contacting
    0.45
    ELS
    0.45
    ↵
    0.44
     aiding
    0.44
    occup
    0.44
     alternatively
    0.43
     ,
    0.42
     soil
    0.42
    POSITIVE LOGITS
    ക്കാരി
    0.47
    考核
    0.46
     ત્ર
    0.46
    графія
    0.46
    她在
    0.45
     میدان
    0.45
     ketiga
    0.45
    连衣裙
    0.45
     ایجاد
    0.44
    强调
    0.44
    Activations Density 0.000%

    No Known Activations