© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129670
    Prev
    Next
    INDEX
    Explanations

    replacement / swapping / exchanging

    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
    Not in Any Lists

    No Comments

    Negative Logits
     those
    -0.09
    那些
    -0.08
     some
    -0.06
     thofe
    -0.06
    force
    -0.06
     попы
    -0.06
     supposed
    -0.06
     Those
    -0.06
    哪些
    -0.06
    those
    -0.06
    POSITIVE LOGITS
    替换
    0.08
    更换
    0.07
    离开了
    0.07
    Otro
    0.07
    geoLocation
    0.07
     luxuri
    0.07
    replaceable
    0.07
     değiştir
    0.07
    Spacer
    0.07
     swapping
    0.07
    Activations Density 0.003%

    No Known Activations