© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13953
    Prev
    Next
    INDEX
    Explanations

    clean and neat

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

    real world focus

    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_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
    цтва
    0.49
     électrique
    0.41
    าย
    0.41
     rendez
    0.41
     ¹
    0.41
    ழ்த்த
    0.41
    ഋ
    0.41
    تها
    0.41
     kræ
    0.41
     présent
    0.40
    POSITIVE LOGITS
    varphi
    0.49
     הכ
    0.49
    DRO
    0.48
    存在
    0.47
     Jimenez
    0.47
    𝓸
    0.47
    C
    0.46
    酉
    0.46
     Westbrook
    0.46
    很重要
    0.46
    Activations Density 0.001%

    No Known Activations