© 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. 55856
    Prev
    Next
    INDEX
    Explanations

    productos, Produkte, produsen

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

    produkty, products, merchandise

    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
     ஏற்றுக்கொள்ள
    0.49
     Helms
    0.48
     aloof
    0.48
    ствий
    0.47
    acity
    0.47
     ກ
    0.47
    akkh
    0.45
    estep
    0.45
    ັກ
    0.45
     丶
    0.45
    POSITIVE LOGITS
     productos
    0.55
     produkty
    0.54
     waarde
    0.54
     Produkte
    0.52
     produse
    0.52
     producten
    0.50
    Desde
    0.49
     prodotti
    0.48
     jeune
    0.48
     beteg
    0.48
    Activations Density 0.000%

    No Known Activations