© 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. 231186
    Prev
    Next
    INDEX
    Explanations

    qualifier followed by noun

    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
     oczywiście
    0.50
    cohols
    0.47
     csak
    0.46
     ತೋರಿಸ
    0.45
     ยัง
    0.45
     гуляць
    0.45
    ៏
    0.44
     inversely
    0.44
     امیدوار
    0.44
     يدل
    0.44
    POSITIVE LOGITS
     CBS
    0.40
     Somehow
    0.39
    URIComponent
    0.39
     ‘
    0.38
     lifegu
    0.37
    혀
    0.37
     security
    0.37
     IMC
    0.37
     Integrity
    0.37
     transpired
    0.36
    Activations Density 0.078%

    No Known Activations