© 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. 31-GEMMASCOPE-2-RES-262K
    7. 196504
    Prev
    Next
    INDEX
    Explanations

    find/had/found/children/leaders

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

    non-english text and attraction

    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_262k_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
     まで
    0.55
     学校
    0.49
    <unused32>
    0.49
     Subsect
    0.47
    seagreen
    0.47
    Themes
    0.47
    <unused94>
    0.47
     Studium
    0.47
     连接
    0.47
     テーマ
    0.47
    POSITIVE LOGITS
    親
    0.50
     щ
    0.47
    iz
    0.45
    了大
    0.44
     лист
    0.44
    임
    0.44
    н
    0.43
    ц
    0.43
     дом
    0.43
    原本
    0.42
    Activations Density 0.000%

    No Known Activations