© 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. 51651
    Prev
    Next
    INDEX
    Explanations

    placing or placed something

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

    place orders or placement

    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
    that
    0.56
    Whether
    0.53
    3
    0.52
     μιας
    0.52
     صرف
    0.50
    ปรุง
    0.50
     শাসন
    0.49
    ε
    0.48
     случаи
    0.48
    ܝܢ
    0.48
    POSITIVE LOGITS
     placed
    1.22
     Placement
    1.18
     coloca
    1.12
     Placing
    1.12
     placing
    1.08
    placed
    1.08
     placement
    1.06
     colocar
    1.00
     placé
    0.98
     placés
    0.98
    Activations Density 0.048%

    No Known Activations