© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 8655
    Prev
    Next
    INDEX
    Explanations

    countries and their associated words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åt
    1.27
     phường
    1.19
    দের
    1.15
    عت
    1.13
    kommen
    1.13
     качестве
    1.12
     مطلب
    1.09
    슨
    1.08
    tores
    1.08
    는
    1.04
    POSITIVE LOGITS
    ओं
    1.39
    ী
    1.37
    علی
    1.26
    और
    1.24
    и
    1.20
    لوب
    1.19
    hip
    1.19
    lı
    1.16
    sulfanyl
    1.16
    Cheerful
    1.16
    Activations Density 0.078%

    No Known Activations