© 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. 25835
    Prev
    Next
    INDEX
    Explanations

    complete replacement

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

    full, entirely, completely

    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
    раху
    0.46
    หลาย
    0.45
     Nhiều
    0.43
    묽
    0.42
     moderate
    0.39
    ༣
    0.39
    动态
    0.38
     molte
    0.38
    俏
    0.38
     subtly
    0.38
    POSITIVE LOGITS
     повністю
    1.50
     полностью
    1.48
     સંપૂર્ણ
    1.40
     entirely
    1.34
    全是
    1.34
     exclusively
    1.33
     completely
    1.32
     সম্পূর্ণরূপে
    1.32
     fully
    1.28
     volledig
    1.27
    Activations Density 0.193%

    No Known Activations