© 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. 68566
    Prev
    Next
    INDEX
    Explanations

    "The" followed by a noun

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

    commitment to, seemingly perfect, wealth responsibly, stranded, successful partnership

    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
     ورق
    0.45
    пециа
    0.43
     Leaders
    0.43
    три
    0.42
     Female
    0.41
    ศ
    0.41
     жы
    0.40
    А
    0.40
    就是在
    0.40
    тни
    0.40
    POSITIVE LOGITS
     {-
    0.47
     pendidikan
    0.46
     змен
    0.45
    𝗺
    0.45
     మన
    0.44
     reductions
    0.44
     inverses
    0.44
     принцип
    0.44
     તમે
    0.44
    گنڈ
    0.43
    Activations Density 0.001%

    No Known Activations