© 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. 148330
    Prev
    Next
    INDEX
    Explanations

    offering discounts and showing information

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

    youth, teen, student demographics

    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
    で使用
    0.50
     ساخته
    0.50
     embank
    0.49
     locom
    0.47
     внешний
    0.47
    竜
    0.47
     என்க
    0.47
     किल्ला
    0.46
     pommes
    0.46
    Есть
    0.46
    POSITIVE LOGITS
     Youth
    0.41
    Muj
    0.40
     Miscellaneous
    0.40
     içeren
    0.39
    其他
    0.39
     Enough
    0.39
    سكر
    0.39
    氛
    0.39
     Luxor
    0.38
    Merk
    0.38
    Activations Density 0.001%

    No Known Activations