© 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. 209910
    Prev
    Next
    INDEX
    Explanations

    a, to, an, ,

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

    explaining AI and human comparisons

    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
     informacija
    0.49
     hydropon
    0.45
     butt
    0.45
    手中
    0.44
     tujuan
    0.44
     uhr
    0.43
     plummet
    0.43
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.42
     lives
    0.42
     completely
    0.42
    POSITIVE LOGITS
     четы
    0.54
    мени
    0.51
     рады
    0.49
    л
    0.48
    ан
    0.48
    ай
    0.47
    趣味
    0.47
    Factories
    0.47
     есте
    0.47
    Произ
    0.47
    Activations Density 0.000%

    No Known Activations