© 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. 151528
    Prev
    Next
    INDEX
    Explanations

    links, If, With, promptly

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

    markdown formatting

    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
    节
    0.49
    的产品
    0.48
    IS
    0.47
    PLC
    0.45
     favore
    0.45
     otorg
    0.44
     закреп
    0.43
    电气
    0.42
     =>
    0.40
     نصف
    0.40
    POSITIVE LOGITS
    abdomen
    0.54
     Entom
    0.49
     Pittsburg
    0.47
     ಕೆಲವು
    0.47
     DENUMIRE
    0.46
     प्रशिक्षण
    0.44
     TRAINING
    0.43
    renamiento
    0.43
    媜
    0.43
     Training
    0.42
    Activations Density 0.001%

    No Known Activations