© 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. 182588
    Prev
    Next
    INDEX
    Explanations

    citing evidence or reasons

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

    showing why

    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
     BasicContainer
    0.44
    今回の
    0.41
    这次
    0.40
    ગત
    0.40
    Routed
    0.40
    <table>
    0.40
     साम
    0.38
     வடிவ
    0.38
    ⎆
    0.38
     commemorative
    0.37
    POSITIVE LOGITS
     why
    0.87
    why
    0.73
     WHY
    0.69
     왜
    0.68
     Why
    0.67
     pourquoi
    0.66
     Почему
    0.66
    Why
    0.65
     reason
    0.64
     mengapa
    0.64
    Activations Density 0.114%

    No Known Activations