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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 835
    Prev
    Next
    INDEX
    Explanations

    pathetic/fucking/idiot/shitty

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

    …

    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
     :-)
    0.68
     ;-)
    0.56
    :-)
    0.56
     ????
    0.55
     commensurate
    0.54
     !!!!!
    0.54
     IMHO
    0.54
     !!!!
    0.51
     ???
    0.49
     appreciably
    0.49
    POSITIVE LOGITS
    -"
    0.78
    -...
    0.77
     Taehyung
    0.76
     Jungkook
    0.74
     fucking
    0.73
     pathetic
    0.68
    ㅡ
    0.68
     fucked
    0.65
     shitty
    0.64
     idiot
    0.62
    Activations Density 0.129%

    No Known Activations