© 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. 45502
    Prev
    Next
    INDEX
    Explanations

    new, was, Mother, elegant, 4

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

    create complex, behind my, dishes placed, backed by

    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
    ↵↵
    0.47
    🐐
    0.46
    ıld
    0.45
     المتوسط
    0.39
    َا
    0.38
     promedio
    0.37
    aid
    0.37
    ;
    0.37
    goat
    0.36
    <tr>
    0.36
    POSITIVE LOGITS
     nimeni
    0.49
    বন্দর
    0.48
    adiene
    0.48
     機能
    0.47
     หน้า
    0.46
    形態
    0.45
    ักษณ์
    0.45
     परस्पर
    0.45
    ับสน
    0.45
    แตกต่าง
    0.44
    Activations Density 0.000%

    No Known Activations