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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7586
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ️⃣
    1.70
    ة
    1.42
    ⃣
    1.31
    ת
    1.31
    ed
    1.27
    oretically
    1.26
    ت
    1.24
    edics
    1.14
    я
    1.11
    нодоро
    1.09
    POSITIVE LOGITS
    ราะห์
    1.07
    ۔
    1.04
    ริญ
    1.02
    utico
    1.01
    ミス
    1.00
     України
    1.00
     文件
    1.00
    写真
    1.00
     anterior
    0.99
     él
    0.98
    Activations Density 0.000%

    No Known Activations