© 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. 9165
    Prev
    Next
    INDEX
    Explanations

    names starting with Ke

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

    ke, ket, keras, kernel, kevin

    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
    Essentials
    0.41
     koron
    0.40
     essentials
    0.39
    ัพ
    0.39
     現
    0.39
     Skop
    0.39
     ignoreString
    0.38
    TAK
    0.38
     usr
    0.38
    кто
    0.38
    POSITIVE LOGITS
     케
    0.50
     Keegan
    0.47
     অনুরূপ
    0.44
     ケ
    0.42
     ke
    0.41
     Keystone
    0.41
     Ке
    0.41
     keen
    0.41
    riwal
    0.40
     ке
    0.40
    Activations Density 0.064%

    No Known Activations