© 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. 242614
    Prev
    Next
    INDEX
    Explanations

    Xbox, games, travel, president

    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
    وزیشن
    0.49
    濰
    0.48
    واعد
    0.47
     Monde
    0.45
     levantar
    0.45
     fortfarande
    0.45
    子公司
    0.45
     decreases
    0.44
    ग्गा
    0.44
     suboptimal
    0.43
    POSITIVE LOGITS
    a
    0.52
    გ
    0.49
     পাঠ
    0.47
     saath
    0.47
     ያስ
    0.46
     참고
    0.46
     коми
    0.46
     חיי
    0.46
    ⚭
    0.46
    ffi
    0.45
    Activations Density 0.001%

    No Known Activations