© 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. 227498
    Prev
    Next
    INDEX
    Explanations

    real estate buyer advice

    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
    йга
    0.55
    нали
    0.52
    лган
    0.51
    ियां
    0.50
    делать
    0.50
    भारत
    0.49
    ह
    0.49
    ผ
    0.48
    нями
    0.48
    мыми
    0.48
    POSITIVE LOGITS
     Anfield
    0.47
    uiDesigner
    0.46
     buyers
    0.45
    kusen
    0.44
     December
    0.44
     Albright
    0.44
     walked
    0.43
     Viewed
    0.43
     আনুষ্ঠানিক
    0.43
     റേ
    0.43
    Activations Density 0.001%

    No Known Activations