© 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. 101863
    Prev
    Next
    INDEX
    Explanations

    Korean War reunions

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

    simulation site

    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
    숟
    0.55
    پاکستان
    0.52
     creación
    0.51
    ساز
    0.51
     dostęp
    0.51
    سازی
    0.50
     conforming
    0.50
    Аль
    0.50
    پیش
    0.50
     ću
    0.50
    POSITIVE LOGITS
    irth
    0.55
    ='
    0.50
    isch
    0.48
    aches
    0.47
    ='',
    0.46
     குறித்து
    0.45
    amin
    0.45
     is
    0.45
     isset
    0.45
    ias
    0.45
    Activations Density 0.000%

    No Known Activations