© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 13307
    Prev
    Next
    INDEX
    Explanations

    intensifiers and swear words

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

    profanity and expletives

    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_31_width_262k_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
     এবং
    0.60
     និង
    0.59
     và
    0.57
     Alessandro
    0.56
    )/\
    0.56
     Các
    0.55
    )|^{
    0.55
    và
    0.55
     Ông
    0.54
     और
    0.52
    POSITIVE LOGITS
     damn
    0.80
    damn
    0.78
     darn
    0.69
     damned
    0.67
     fucking
    0.59
     bloody
    0.51
     downright
    0.49
    Damn
    0.49
     freaking
    0.47
     whopping
    0.47
    Activations Density 0.036%

    No Known Activations