Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 420
    Prev
    Next
    INDEX
    Explanations

    ordinal number

    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_22_width_16k_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
    יות
    0.87
    이
    0.85
     war
    0.67
    tenths
    0.64
    น
    0.64
     permutations
    0.61
    ்
    0.61
     cog
    0.61
     monoc
    0.60
    ities
    0.60
    POSITIVE LOGITS
    st
    1.90
    ️⃣
    1.42
    хбет
    1.39
    xbet
    1.35
    ⃣
    1.22
    stArray
    1.18
    ⃙
    1.15
    ⁄
    1.09
    dbjc
    1.09
    fichier
    1.07
    Activations Density 0.650%

    No Known Activations