© 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. 219384
    Prev
    Next
    INDEX
    Explanations

    portfolio samples. or

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

    vowed to, compete with, convince a

    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
     людини
    0.42
     aldı
    0.41
     والر
    0.41
     مارت
    0.41
    heber
    0.41
    ó
    0.41
     congregations
    0.40
     கடல்
    0.40
    ⛺
    0.40
     آمریکا
    0.39
    POSITIVE LOGITS
     свої
    0.48
     pessimistic
    0.47
    ina
    0.46
     रहें
    0.43
     conclusive
    0.42
    msub
    0.41
     दुष्प्रभावों
    0.41
     serialized
    0.41
    娯
    0.41
    岡
    0.40
    Activations Density 0.001%

    No Known Activations