© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 343
    Prev
    Next
    INDEX
    Explanations

    Gemma, Luxembourg, girl

    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
     başkan
    0.16
     الجميع
    0.15
    ੪
    0.15
    ഹ്ലാദ
    0.15
     bahwa
    0.15
    quele
    0.15
    ل
    0.14
     त्यांची
    0.14
     empres
    0.14
    ന്തപു
    0.14
    POSITIVE LOGITS
    .
    0.21
    :
    0.20
    と呼ばれる
    0.19
    ↵
    0.19
    ®.
    0.19
    ®
    0.18
    ™
    0.18
    ,
    0.18
    ®,
    0.17
    （
    0.16
    Activations Density 12.366%

    No Known Activations