© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128014
    Prev
    Next
    INDEX
    Explanations

    black men/teens, gay student

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     work
    -0.06
    ोलिक
    -0.06
    work
    -0.06
     Spike
    -0.06
    bonding
    -0.06
    marks
    -0.05
    film
    -0.05
    iscope
    -0.05
     pain
    -0.05
     reception
    -0.05
    POSITIVE LOGITS
     forcibly
    0.06
     предвари
    0.06
    atemala
    0.06
    可以直接
    0.06
     Remaining
    0.06
     મારા
    0.06
    事前
    0.06
     AutoML
    0.06
     préal
    0.06
    Remaining
    0.06
    Activations Density 0.001%

    No Known Activations