© 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. 102666
    Prev
    Next
    INDEX
    Explanations

    market for, pursue a, contributors for, ranks next

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

    lawyer translator trade

    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
     "-//
    0.45
    面に
    0.44
    었어요
    0.44
     Sweep
    0.43
     Consecutive
    0.43
     Highway
    0.41
    inée
    0.41
    咵
    0.41
     consecutively
    0.41
     consecutive
    0.41
    POSITIVE LOGITS
     provavelmente
    0.55
    arschijnlijk
    0.55
     但是
    0.49
     آب
    0.48
    但我
    0.48
     ancak
    0.48
     synthesize
    0.47
     minecraft
    0.46
     لیکن
    0.46
     رفتار
    0.46
    Activations Density 0.001%

    No Known Activations