© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8633
    Prev
    Next
    INDEX
    Explanations

    deep concepts (state, space, brain)

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

    deep learning

    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_40_width_16k_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
     অভিহিত
    0.43
     Pais
    0.42
    pais
    0.41
     الحركة
    0.40
     কিল
    0.39
     pais
    0.39
    ilidade
    0.39
    㕵
    0.38
    тинен
    0.38
    τικών
    0.38
    POSITIVE LOGITS
     deep
    1.72
    deep
    1.60
    深
    1.56
     Deep
    1.54
    Deep
    1.53
     глубо
    1.51
     깊
    1.41
     深
    1.39
    깊
    1.38
     profunda
    1.36
    Activations Density 0.102%

    No Known Activations