© 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. 129422
    Prev
    Next
    INDEX
    Explanations

    buy one

    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
     a
    -0.07
     populaire
    -0.07
     인기
    -0.07
    readable
    -0.06
     popular
    -0.06
     supplement
    -0.06
     उनके
    -0.06
     পাশ্চ
    -0.06
    popular
    -0.06
    সেন
    -0.06
    POSITIVE LOGITS
    反复
    0.06
    做
    0.06
    故意
    0.06
     ڈیزائن
    0.06
     dovrà
    0.06
     disguised
    0.06
    和其他
    0.06
    हमने
    0.06
     repeated
    0.06
     campsites
    0.05
    Activations Density 0.007%

    No Known Activations