© 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. 787
    Prev
    Next
    INDEX
    Explanations

    Research Skills or Prevention report

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

    numbers followed by text

    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
    ↵
    0.34
    无
    0.26
     
    0.25
    时
    0.25
    ↵↵
    0.25
     the
    0.25
     a
    0.24
    的时候
    0.24
    ที่
    0.22
    成
    0.22
    POSITIVE LOGITS
     diskusi
    0.30
    autoarima
    0.30
    sadquotes
    0.29
    <unused402>
    0.29
     decidiu
    0.28
     conseguiu
    0.28
     socialista
    0.28
    <unused477>
    0.28
    <unused468>
    0.27
    <unused1749>
    0.27
    Activations Density 0.092%

    No Known Activations