© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2089
    Prev
    Next
    INDEX
    Explanations

    offensive or inappropriate content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     bakalım
    0.84
     saver
    0.71
     unbeaten
    0.69
    спери
    0.67
     दिलचस्प
    0.67
    pherd
    0.67
    ꒪
    0.66
    দর
    0.65
     Scissors
    0.65
    PickerController
    0.64
    POSITIVE LOGITS
     sexual
    1.69
     sexually
    1.68
     offensive
    1.68
     content
    1.56
     depictions
    1.55
     vulgar
    1.52
     hateful
    1.52
     derogatory
    1.51
     inappropriate
    1.49
     misog
    1.49
    Activations Density 2.982%

    No Known Activations