© 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. 242885
    Prev
    Next
    INDEX
    Explanations

    verb followed by a specific preposition

    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
    트를
    0.49
     skate
    0.46
    ਟ
    0.46
    檚
    0.45
    推出的
    0.44
     lacrosse
    0.43
    रेख
    0.43
    轆
    0.43
     conclure
    0.43
     hitta
    0.43
    POSITIVE LOGITS
     тобто
    0.48
    所以我
    0.47
    UIButton
    0.46
     洋
    0.45
    我是
    0.44
    Nau
    0.43
     изготов
    0.43
     моя
    0.43
    এখানে
    0.43
     việc
    0.43
    Activations Density 0.000%

    No Known Activations