© 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. 5577
    Prev
    Next
    INDEX
    Explanations

    French or Romanian common words

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

    magic remains, passive income, scaling accurately

    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
    ；
    0.46
    を使用
    0.43
    。
    0.43
    ↵
    0.42
     ร้าน
    0.41
     ซึ่ง
    0.40
    ().
    0.39
    使用
    0.39
    ）
    0.39
     。
    0.38
    POSITIVE LOGITS
     artık
    0.40
     contribuir
    0.39
     entusias
    0.38
     energías
    0.38
     solidar
    0.38
     consciência
    0.38
     fortalecer
    0.37
     catalyze
    0.37
     passionately
    0.37
     forstå
    0.37
    Activations Density 0.000%

    No Known Activations