© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1468
    Prev
    Next
    INDEX
    Explanations

    spitting facts

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

    The neuron detects vulgar or profane words (i.e. swear words and expletives).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    เพียง
    0.60
    ppled
    0.57
    ี
    0.55
     photographs
    0.53
    得以
    0.52
     strikingly
    0.52
     exquisitely
    0.52
     separate
    0.51
     विशिष्ट
    0.51
    щая
    0.50
    POSITIVE LOGITS
    💩
    0.81
     nigga
    0.76
     fucking
    0.75
    🖕
    0.75
    fuck
    0.75
     shit
    0.73
     crap
    0.73
     fucked
    0.73
     outta
    0.70
     यार
    0.69
    Activations Density 0.001%

    No Known Activations