© 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. 62463
    Prev
    Next
    INDEX
    Explanations

    organizations and entities

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

    unchecked behavior, factoring difficulty

    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
    、
    0.54
    3
    0.51
     등을
    0.48
    testen
    0.46
    production
    0.46
    6
    0.45
     должен
    0.45
    7
    0.44
    起こ
    0.44
    或
    0.43
    POSITIVE LOGITS
     teenagers
    0.56
    পিং
    0.49
     każdej
    0.46
     আউট
    0.45
     kiddos
    0.45
     كلهم
    0.45
     jejich
    0.44
     njima
    0.44
     bebé
    0.44
     încep
    0.44
    Activations Density 0.001%

    No Known Activations