© 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. 14652
    Prev
    Next
    INDEX
    Explanations

    by or as

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

    in or as

    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
     көзге
    0.45
     которому
    0.44
     అది
    0.43
     ktorá
    0.43
    ដែល
    0.42
    幺
    0.40
     যেটি
    0.40
     которым
    0.39
     რომელიც
    0.39
     Yoh
    0.39
    POSITIVE LOGITS
    using
    0.42
     بواسطة
    0.41
     by
    0.39
     medium
    0.38
    by
    0.38
     pursuant
    0.38
    enriched
    0.38
     &&
    0.38
     with
    0.37
     oleh
    0.37
    Activations Density 0.184%

    No Known Activations