© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 15018
    Prev
    Next
    INDEX
    Explanations

    her son, duck quack, feminist man

    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
    큽
    1.02
     ঃ
    0.95
     عندنا
    0.95
    ります
    0.94
     Вам
    0.92
     muß
    0.91
     Bldg
    0.90
    ๑
    0.89
    
    0.85
     наших
    0.85
    POSITIVE LOGITS
    TikTok
    1.36
     reportedly
    1.24
     YouTuber
    1.24
     कथित
    1.20
     kvůli
    1.19
     TikTok
    1.19
    Notably
    1.14
     netizens
    1.13
     allegedly
    1.11
     XNUMX
    1.10
    Activations Density 0.022%

    No Known Activations