© 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
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9075
    Prev
    Next
    INDEX
    Explanations

    math and programming constructs

    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
    م
    2.04
    Ano
    1.40
    स
    1.38
    е
    1.38
    ت
    1.38
    ية
    1.37
    о
    1.35
    ine
    1.32
    د
    1.28
     ano
    1.27
    POSITIVE LOGITS
    ǎng
    1.40
     Puff
    1.39
     terrified
    1.39
     Gottfried
    1.29
    itating
    1.27
    isher
    1.27
    cludes
    1.26
    ছিল
    1.25
    gium
    1.24
     conveyor
    1.23
    Activations Density 0.000%

    No Known Activations