© 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. 70413
    Prev
    Next
    INDEX
    Explanations

    must be

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

    obligation and necessity

    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
    잿
    0.52
    морфи
    0.51
    marès
    0.50
    менение
    0.48
    轻易
    0.48
    历史上
    0.46
    ovať
    0.46
    まし
    0.46
    ủi
    0.45
    渋
    0.45
    POSITIVE LOGITS
     before
    0.56
     to
    0.54
     acclimat
    0.51
     ต้อง
    0.50
     authenticated
    0.49
     অবশ্যই
    0.49
     adherence
    0.49
     white
    0.48
    angers
    0.48
     обязательно
    0.48
    Activations Density 0.272%

    No Known Activations