© 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
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1396
    Prev
    Next
    INDEX
    Explanations

    internet slang and emojis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ã
    1.17
    
    1.06
    :-)
    1.00
     Ã
    1.00
    
    0.94
     muß
    0.90
     Â
    0.90
     {\
    0.89
    Â
    0.89
     ({\
    0.86
    POSITIVE LOGITS
     lmao
    2.31
    🥲
    2.13
    🥹
    2.10
    🥺
    2.06
    🫠
    2.02
     tiktok
    2.02
    🫡
    2.00
    💀
    1.99
    🗿
    1.98
    😭😭
    1.90
    Activations Density 0.320%

    No Known Activations