© 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. 60006
    Prev
    Next
    INDEX
    Explanations

    at, in, on, subsequent

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

    prepositions followed by articles

    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
     trên
    0.67
     în
    0.64
     trong
    0.62
     في
    0.61
     onscreen
    0.61
     στο
    0.61
     στην
    0.61
     ở
    0.60
    ใน
    0.60
     tại
    0.57
    POSITIVE LOGITS
    いろんな
    0.41
     बतौर
    0.40
     المختلفة
    0.40
    ันทร์
    0.39
    様子
    0.39
    Без
    0.39
    拿着
    0.38
     עם
    0.38
    iedy
    0.38
    扮演
    0.38
    Activations Density 0.192%

    No Known Activations