© 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. 50095
    Prev
    Next
    INDEX
    Explanations

    congregation of, Champions League

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

    slimy variations

    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
    权益
    0.43
     말미암
    0.42
    ্যেষ্ঠ
    0.41
    اع
    0.41
    锡
    0.39
    quilibrium
    0.39
    ava
    0.38
    贝
    0.38
     Asst
    0.38
    此事
    0.37
    POSITIVE LOGITS
     necesitas
    0.60
    するには
    0.54
     quieras
    0.54
     צריך
    0.52
     нужно
    0.51
    の
    0.51
     строка
    0.50
    な
    0.50
     wymag
    0.50
     biznes
    0.49
    Activations Density 0.000%

    No Known Activations