© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 10665
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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_17_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
     TikTok
    2.69
    🥰
    2.33
    TikTok
    2.31
     🥰
    2.28
    🥲
    2.26
     PFAS
    2.26
    🥹
    2.19
     проє
    2.19
    🫶
    2.18
    🫡
    2.13
    POSITIVE LOGITS
    1.19
      
    1.12
    http
    1.03
    mbox
    1.03
    sprintf
    1.00
     muß
    1.00
     xrange
    1.00
    
    0.98
       
    0.97
    StringBuffer
    0.96
    Activations Density 0.066%

    No Known Activations