© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2429
    Prev
    Next
    INDEX
    Explanations

    speculative suggestions and examples

    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_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
    𝗚
    3.10
    𝗢
    2.53
    𝗟
    2.51
    
    2.46
    𝗩
    2.40
     ain
    2.38
     Kč
    2.38
    𝗝
    2.37
    𝗙
    2.33
    𝗜
    2.30
    POSITIVE LOGITS
    ン
    3.50
    า
    3.02
    ی
    2.93
    ي
    2.88
    ا
    2.86
    ேத்க
    2.79
    ্লিকেশন
    2.73
    𝙙
    2.64
    𝙞
    2.63
    я
    2.57
    Activations Density 0.192%

    No Known Activations