© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 861
    Prev
    Next
    INDEX
    Explanations

    is, lies in, means

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

    defining goals and parts

    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_53_width_65k_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
     ذریع
    0.44
     جبکہ
    0.41
     آنچه
    0.39
    Creates
    0.39
     einschließlich
    0.35
     INCLUDING
    0.35
     takže
    0.35
    ))]
    0.34
     کریں۔
    0.34
     incluindo
    0.34
    POSITIVE LOGITS
     ialah
    1.35
    的是
    1.18
    คือ
    1.18
     adalah
    1.09
     заключается
    1.04
    的就是
    1.03
     lies
    1.00
    在于
    1.00
     है
    0.98
     වන්නේ
    0.98
    Activations Density 0.588%

    No Known Activations