© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30988
    Prev
    Next
    INDEX
    Explanations

    swear words and strong expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﻭ
    -0.94
    ophora
    -0.77
    estina
    -0.70
    YSTAL
    -0.69
    smarty
    -0.68
    ϳ
    -0.68
     On
    -0.66
     ਵ
    -0.66
    {}'.
    -0.65
     alignments
    -0.65
    POSITIVE LOGITS
     crap
    3.23
     hell
    2.97
     shit
    2.83
     heck
    2.72
     living
    2.67
     SHIT
    2.17
    living
    2.13
     HELL
    2.05
    hell
    2.03
    crap
    2.00
    Activations Density 0.021%

    No Known Activations