© 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. 120050
    Prev
    Next
    INDEX
    Explanations

    chain link woven loops

    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
     misguided
    -0.06
     متوسط
    -0.06
    MUSIC
    -0.06
    宣传
    -0.06
     each
    -0.06
     shattered
    -0.06
     avaient
    -0.06
     avait
    -0.06
    ᱛ
    -0.06
     Music
    -0.06
    POSITIVE LOGITS
    两次
    0.07
     exchanged
    0.06
     както
    0.06
     twor
    0.06
     skipped
    0.06
     current
    0.06
     interchanges
    0.06
     ಸ್ಥಾನ
    0.06
     nausea
    0.06
    сподар
    0.06
    Activations Density 0.005%

    No Known Activations