© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2824
    Prev
    Next
    INDEX
    Explanations

    new target

    np_acts-logits-general · gemini-2.5-flash-lite

    internet memes and slang

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
     quelquefois
    0.59
    
    0.57
    :-)
    0.54
    
    0.49
     करीत
    0.48
     ...(
    0.48
    ﹔
    0.48
     Â
    0.48
    
    0.48
     Tetapi
    0.46
    POSITIVE LOGITS
     lmao
    1.48
     fucking
    1.48
     fuck
    1.39
     fucked
    1.34
     shitty
    1.25
     meme
    1.14
    Fuck
    1.13
     idk
    1.13
     shit
    1.12
     memes
    1.11
    Activations Density 0.090%

    No Known Activations